Skip to content
← Back to Glossary

Glossary Atlas

All AI terms A-Z — 876 entries, single page.

Tip: use Ctrl+P to save as PDF.

ABCDEFGHIJKLMNOPQRSTUVWXZ

A

❄️AI Winteryapay-zeka-temelleri
Periods when interest and investment in AI dropped sharply due to the gap between expectations and technical reality.
⚖️AICmatematik-istatistik-optimizasyon
An information criterion that supports model selection by balancing model fit against model complexity.
📊ANOVAmatematik-istatistik-optimizasyon
A method used to test whether there are meaningful differences among the means of multiple groups.
⏳ARIMAmakine-ogrenmesi
A classical model for time series forecasting that combines autoregressive and moving-average components.
🛑Abstentionuretken-yapay-zeka-ve-llm
The ability of a model to avoid fabricating certainty and instead decline or express uncertainty when it is not confident.
📝Abstractive Summarizationdogal-dil-isleme
A generative summarization approach that rewrites source text to produce more natural and dense summaries.
🎯Accuracyveri-bilimi-ve-veri-yonetimi
A quality dimension expressing how correctly a data field reflects the real-world value it represents.
🚨Acoustic Event Detectionses-konusma-audio-ai
A task focused on locating and labeling specific events within an audio stream over time.
🌆Acoustic Scene Classificationses-konusma-audio-ai
A task focused on predicting what environment or context an audio recording comes from.
🎬Actionyapay-zeka-temelleri
The decision output chosen by an agent according to the current state, which produces an effect on the environment.
🔮Action Anticipationbilgisayarli-goru
A task that attempts to predict a future action from a partially observed video stream before it fully unfolds.
🏃Action Recognitionbilgisayarli-goru
A task focused on recognizing action classes from human or object motion in video.
🎯Active Labelingveri-bilimi-ve-veri-yonetimi
An approach that aims to optimize labeling cost by selecting the most useful or uncertain examples for annotation.
🎯Active Learningyapay-zeka-temelleri
A data-efficiency approach in which the model selects the most informative examples and requests labels from a human or expert source.
🎯AdaBoostmakine-ogrenmesi
A boosting method that turns weak learners into a strong ensemble by focusing increasingly on hard examples.
⚡Adam Optimizationmatematik-istatistik-optimizasyon
A popular optimization algorithm that combines adaptive learning rates with momentum-like behavior.
🧱Adaptersuretken-yapay-zeka-ve-llm
A parameter-efficient approach that inserts small modules into the base model to enable task adaptation.
➕Additive Attentionderin-ogrenme
An early attention approach that compares query and context representations through a learnable combination function.
⚖️Adjudication Workflowveri-bilimi-ve-veri-yonetimi
A quality assurance workflow in which conflicting or ambiguous labels are resolved through higher-level review.
📡Affinity Propagationmakine-ogrenmesi
A clustering algorithm that forms clusters through message passing around representative exemplars.
🧮Aggregate Tableveri-muhendisligi-ve-ai-altyapisi
A table structure that stores summarized results derived from detailed data in order to accelerate analytical queries.
🧺Aggregation Featureveri-bilimi-ve-veri-yonetimi
A feature structure that summarizes lower-level records into higher-level signals meaningful for modeling.
🔀Alignment in Translationdogal-dil-isleme
A concept that models which parts of the source text correspond to which parts in the target language.
🅰️Alternative Hypothesismatematik-istatistik-optimizasyon
The hypothesis that argues there is a meaningful effect, difference, or relationship in the data, in contrast to the null hypothesis.
👂Always-On Audio Detectionses-konusma-audio-ai
A system approach that enables low-power sound event detection while a device remains in continuous listening mode.
📦Anchor Boxesbilgisayarli-goru
A design approach that facilitates object detection by using predefined candidate boxes of different scales and aspect ratios.
✍️Annotationyapay-zeka-temelleri
The process of adding meaningful labels, notes, or markings to data so that it becomes usable for model training.
🎭Anonymizationveri-bilimi-ve-veri-yonetimi
The process of transforming personal data so that it can no longer be linked back to a specific individual.
✅Answer Verificationdogal-dil-isleme
A safety layer that aims to verify a generated answer through source evidence, logic checks, or additional model scrutiny.
🎯Approximate Nearest Neighbor Searchveri-muhendisligi-ve-ai-altyapisi
A search approach in high-dimensional vector spaces that prioritizes speed and acceptable proximity over exactness.
🌐Artificial General Intelligence (AGI)yapay-zeka-temelleri
A hypothetical level of AI with human-like flexibility, capable of transferring knowledge across different tasks and contexts.
🧠Artificial Intelligence (AI)yapay-zeka-temelleri
A discipline focused on enabling machines to perform capabilities associated with human intelligence, such as perception, learning, reasoning, and decision-making.
🔍Aspect-Based Sentiment Analysisdogal-dil-isleme
An approach that predicts sentiment for specific aspects or entity dimensions rather than overall sentiment.
🎯Attentionderin-ogrenme
A mechanism that enables a model to learn which parts of the input deserve more focus during prediction.
🎭Attention Maskderin-ogrenme
A control mechanism that determines which positions a model may or may not attend to during attention computation.
📊Attention Score Matrixderin-ogrenme
A matrix structure that numerically represents how much each element in a sequence attends to the others.
🔎Audio Embedding Retrievalses-konusma-audio-ai
An approach that enables acoustic search and content discovery by retrieving similar audio recordings in embedding space.
🏷️Audio Taggingses-konusma-audio-ai
A multi-label task that predicts which sound events are present in an audio clip at the clip level.
📜Audit Trailveri-muhendisligi-ve-ai-altyapisi
A tracking mechanism that records who changed data or processes, when, and how.
🕳️Autoencoderderin-ogrenme
A neural architecture that learns low-dimensional representations by compressing and reconstructing data.
🚨Autoencoder-Based Anomaly Detectionmakine-ogrenmesi
A deep learning approach that learns normal patterns and detects anomalies through reconstruction error.
🕳️Autoencoder-Based Dimensionality Reductionmakine-ogrenmesi
An approach that learns lower-dimensional representations of data through neural-network-based compression.
🎙️Automatic Speech Recognitionses-konusma-audio-ai
The core speech-to-text task aimed at converting human speech into text.
🚗Autonomous Systemyapay-zeka-temelleri
A system capable of handling perception, evaluation, and action generation with little or no human intervention.
➡️Autoregressive Decodinguretken-yapay-zeka-ve-llm
A generation mode in which the model produces output token by token using previous outputs as context.

B

⚙️BFGSmatematik-istatistik-optimizasyon
A quasi-Newton optimization method that approximates second-order information to achieve efficient convergence.
📚BICmatematik-istatistik-optimizasyon
A model selection criterion that applies a stronger penalty for complexity while evaluating model fit.
🔖BIO Taggingdogal-dil-isleme
A classical sequence-labeling scheme that marks entity boundaries with beginning, inside, and outside tags.
🌿BIRCH Clusteringmakine-ogrenmesi
A tree-based method suited to incremental and memory-efficient clustering on large datasets.
🔁Back Translationdogal-dil-isleme
A data augmentation strategy based on translating target-language data back into the source language to create synthetic parallel data.
⏪Backfillveri-muhendisligi-ve-ai-altyapisi
The process of reprocessing historical periods or filling missing historical data gaps after the fact.
🔁Backpropagationderin-ogrenme
The core learning mechanism that propagates loss gradients backward through layers to update weights.
⏪Backpropagation Through Timederin-ogrenme
A method in sequential models where the network is unrolled across time steps and gradients are computed backward.
🧺Baggingmakine-ogrenmesi
An ensemble approach that improves stability by training multiple models on bootstrap samples and combining their outputs.
📦Balanced Batch Samplingveri-bilimi-ve-veri-yonetimi
A sampling strategy that balances learning by maintaining a more controlled class distribution within each training batch.
🧱Basismatematik-istatistik-optimizasyon
A set of linearly independent vectors capable of generating every element of a vector space.
📚Batch Backlogveri-muhendisligi-ve-ai-altyapisi
A load condition in which scheduled batch jobs accumulate in the processing queue because they cannot complete on time.
🧰Batch Jobveri-muhendisligi-ve-ai-altyapisi
A bulk data processing task that runs according to a schedule or trigger.
📦Batch Learningyapay-zeka-temelleri
A learning approach in which the model is trained on a fixed dataset in batches and updated periodically.
📊Batch Normalizationderin-ogrenme
A technique that normalizes intermediate activations at the mini-batch level to accelerate training and provide partial regularization.
📦Batch Processingveri-muhendisligi-ve-ai-altyapisi
A processing approach in which data is handled in bulk at scheduled intervals and results are produced periodically.
🧮Bayes' Theoremmatematik-istatistik-optimizasyon
A fundamental probability theorem that allows updating the probability of a hypothesis as new observations arrive.
📘Bayesian Linear Regressionmakine-ogrenmesi
A linear regression approach that treats model parameters as probability distributions rather than fixed values.
🕸️Bayesian Networkmakine-ogrenmesi
A probabilistic model that represents conditional dependencies among variables through a directed graph structure.
🧠Bayesian Optimizationmakine-ogrenmesi
A sample-efficient optimization method that intelligently selects new hyperparameter candidates by learning from past trials.
📡Beamformingses-konusma-audio-ai
A spatial audio processing technique that combines multiple microphone signals directionally to enhance a target source.
📏Benchmarkyapay-zeka-temelleri
A standardized framework of data, metrics, and evaluation used to compare different models on the same task.
0️⃣Bernoulli Distributionmatematik-istatistik-optimizasyon
A discrete distribution that models single-step random experiments with only two possible outcomes.
🟦Beta Distributionmatematik-istatistik-optimizasyon
A continuous distribution especially well suited for modeling proportions and probabilities between 0 and 1.
🧬Beta-VAEderin-ogrenme
A variational model that strengthens VAE regularization to learn more disentangled factors in latent space.
🎯Biasmatematik-istatistik-optimizasyon
A statistical concept describing the tendency of an estimator to systematically deviate from the true value.
↔️Bidirectional RNNderin-ogrenme
An RNN structure that processes sequence information in both forward and backward directions to provide richer context.
🔢Binomial Distributionmatematik-istatistik-optimizasyon
A discrete distribution that models the number of successes in a fixed number of independent Bernoulli trials.
🕊️Bioacoustic Classificationses-konusma-audio-ai
An environmental audio analysis task that automatically recognizes birds, insects, marine mammals, or other biological sound sources.
💥Blast Radius Analysisveri-muhendisligi-ve-ai-altyapisi
A risk analysis approach that measures how many assets and which critical processes may be affected by a data change or failure.
♻️Bootstrapmatematik-istatistik-optimizasyon
A method that repeatedly resamples the data to estimate uncertainty, confidence intervals, and performance distributions.
🫧Bottleneck Layerderin-ogrenme
A narrow intermediate layer that forces the model to compress information and learn more compact representations.
🪡Boundary-Aware Segmentationbilgisayarli-goru
A segmentation approach that aims to improve mask quality by modeling object boundaries more precisely.
⬛Bounding Box Regressionbilgisayarli-goru
A detection subtask that predicts an object’s location and size in an image as coordinates.
🎯Brier Scorematematik-istatistik-optimizasyon
A score that jointly evaluates the accuracy and calibration quality of probabilistic predictions.
💼Business Metadataveri-muhendisligi-ve-ai-altyapisi
The metadata layer that explains the business meaning, usage purpose, and enterprise definitions of data assets.
🔡Byte Pair Encodingdogal-dil-isleme
A tokenization method that builds a data-driven subword vocabulary by learning frequent subunit merges.
💾Byte-Level Tokenizationdogal-dil-isleme
An approach that tokenizes text at the byte level rather than character level to build more robust representations for multilingual and noisy input.

C

🗺️CNN Feature Mapsbilgisayarli-goru
Intermediate representations learned by convolutional layers that carry visual patterns at different abstraction levels.
🧩CTC Decodingses-konusma-audio-ai
A core learning and decoding approach that helps recover text from speech sequences with unknown alignments.
🎛️Calibrated Classificationmakine-ogrenmesi
An approach that aims to make a classifier’s probability outputs more consistent with true observed frequencies.
🧪Calibrationmatematik-istatistik-optimizasyon
A property describing how well a model’s predicted probabilities align with actual observed frequencies.
🧱Canonicalizationveri-bilimi-ve-veri-yonetimi
The process of converting different representations of the same information into one standard canonical form.
🐱CatBoostmakine-ogrenmesi
An advanced ensemble method that combines boosting with strong native handling of categorical variables.
🧠Catastrophic Forgettinguretken-yapay-zeka-ve-llm
The problem in which a model loses some of its prior general abilities while being adapted to new tasks.
🧹Category Standardizationveri-bilimi-ve-veri-yonetimi
The process of unifying different spellings, abbreviations, or formats representing the same concept into one standard form.
⏩Causal Attentionderin-ogrenme
An autoregressive attention structure that allows a token to attend only to positions at or before itself.
⏩Causal Language Modelingdogal-dil-isleme
An autoregressive learning objective based on predicting the next token using only previous context.
🗄️Cell Statederin-ogrenme
A memory pathway in LSTM architectures that carries long-term information more directly.
🔗Chain Rulederin-ogrenme
The rule for computing derivatives of composed functions and the mathematical foundation of backpropagation.
🪜Chain-of-Thought Promptingdogal-dil-isleme
A prompting approach that encourages the model to generate intermediate reasoning steps before the final answer.
🔄Change Data Captureveri-bilimi-ve-veri-yonetimi
An approach for tracking data changes in source systems and propagating them to downstream systems in near real time.
🌐Change Propagation Analysisveri-muhendisligi-ve-ai-altyapisi
The process of analyzing how a change in a data asset or business logic will propagate across the platform.
🎚️Channel Attentionderin-ogrenme
An attention mechanism that emphasizes more informative feature channels rather than treating all of them equally.
📶Channel Capacitymatematik-istatistik-optimizasyon
The theoretical maximum amount of information that a communication channel can transmit without error.
🎛️Channel Compensationses-konusma-audio-ai
A speaker recognition approach aimed at reducing voice variation caused by microphone, transmission, or recording-environment differences.
📉Chart Understandingbilgisayarli-goru
A task that converts bar charts, line graphs, and similar visual presentations into structured data and semantic interpretation.
💾Checkpointed Backpropagationderin-ogrenme
A training technique that reduces memory usage by not storing all intermediate activations and recomputing them when needed.
🧮Chi-Square Distributionmatematik-istatistik-optimizasyon
A distribution derived from the sum of squared standard normal variables and widely used in statistical testing.
🔗Citation Groundinguretken-yapay-zeka-ve-llm
An approach that improves trust by explicitly showing the source passages supporting the generated answer.
⚖️Class Imbalanceveri-bilimi-ve-veri-yonetimi
A condition in which some classes are heavily represented while others are represented only sparsely in a dataset.
🏋️Class Weightingveri-bilimi-ve-veri-yonetimi
An approach that rebalances model learning by increasing the error cost of underrepresented classes.
🧠Closed-Book Question Answeringdogal-dil-isleme
An approach that answers questions using only the information stored in model parameters, without external document access.
🧊Cold Storage Tierveri-muhendisligi-ve-ai-altyapisi
An approach in which rarely accessed but still required data is kept in a low-cost storage tier.
🤝Collaborative Filteringmakine-ogrenmesi
A core recommendation approach that generates suggestions through similar users or similar items.
💡Color Constancybilgisayarli-goru
An image-processing approach that aims to perceive object colors more consistently under varying illumination conditions.
🎨Color Space Conversionbilgisayarli-goru
A process that transforms an image into representations other than RGB to make certain visual signals more accessible.
📑Column-Level Lineageveri-muhendisligi-ve-ai-altyapisi
A detailed lineage level that traces which source columns each field was derived from and how it was transformed.
🧩Completenessveri-bilimi-ve-veri-yonetimi
A data quality dimension describing how fully expected fields, records, or business scope are present in a dataset.
🕸️Computational Graphderin-ogrenme
A structure that represents model operations as nodes and edges, making automatic differentiation easier.
⚠️Condition Numbermatematik-istatistik-optimizasyon
An important linear algebra indicator that measures how numerically sensitive or unstable a matrix is.
🔗Conditional Probabilitymatematik-istatistik-optimizasyon
A concept that measures how likely an event is given that another event has already occurred.
🧷Conditional Random Fieldmakine-ogrenmesi
A conditional probabilistic graphical model used especially in sequential labeling problems.
🧭Conformed Dimensionveri-muhendisligi-ve-ai-altyapisi
A dimension structure reused across different fact tables and business domains with shared meaning.
🤝Consensus Clusteringmakine-ogrenmesi
An approach that combines multiple clustering results to obtain a more stable and reliable cluster structure.
🗳️Consensus Labelingveri-bilimi-ve-veri-yonetimi
An approach in which multiple annotators’ judgments are combined to determine the final label for a data instance.
✅Consent Managementveri-bilimi-ve-veri-yonetimi
The consent-based management of the purposes, scope, and duration under which personal data may be processed.
📈Consistencymatematik-istatistik-optimizasyon
The property of an estimator converging to the true value as the sample size grows.
📜Constitutional AIuretken-yapay-zeka-ve-llm
An alignment approach that tries to guide model behavior through explicit principle sets and normative rules.
⛓️Constrained Optimizationmatematik-istatistik-optimizasyon
An optimization approach in which the solution must satisfy not only the objective function but also specified constraints.
👥Consumer Groupveri-muhendisligi-ve-ai-altyapisi
A group of consumer instances that read from the same stream in a balanced and parallel way.
🧾Content-Based Filteringmakine-ogrenmesi
A recommendation method that relies on item features and a user's historical preference profile.
🪟Context Windowderin-ogrenme
The maximum sequence length that a Transformer model can process in a single pass.
🌐Contextual Embeddingsdogal-dil-isleme
A modern embedding approach in which the same word receives different vectors in different contexts.
🔄Continued Pretrainingdogal-dil-isleme
The process of further training a pretrained language model on new data to improve general or domain-specific knowledge.
📦Continuous Batchinguretken-yapay-zeka-ve-llm
A serving approach that increases throughput by dynamically merging requests arriving at different times into the same processing flow.
📈Continuous Emotion Predictionses-konusma-audio-ai
An approach that models emotion as time-varying dimensional values rather than fixed categories.
🔒Contractive Autoencoderderin-ogrenme
A type of autoencoder that uses an additional penalty to learn more stable latent representations under input perturbations.
🧲Contrastive Embedding Learningdogal-dil-isleme
An approach that learns semantic representations by bringing similar texts closer and pushing dissimilar texts apart in vector space.
🧲Contrastive Visual Pretrainingbilgisayarli-goru
An approach that learns strong visual features by bringing similar images close and pushing dissimilar ones apart in representation space.
🛤️Convex Optimizationmatematik-istatistik-optimizasyon
A class of optimization problems where the objective and constraints satisfy favorable geometric conditions that enable more reliable solutions.
🧱Convolutionderin-ogrenme
The fundamental operation of CNNs that captures spatial patterns through local filters.
🔁Coreference Resolutiondogal-dil-isleme
A task that determines whether different expressions in text refer to the same entity or event.
🔗Correlationmatematik-istatistik-optimizasyon
A standardized measure of the direction and strength of the linear relationship between two variables.
💸Cost-Sensitive Classificationmakine-ogrenmesi
An approach that incorporates different misclassification costs into the decision process instead of treating all errors equally.
🔄Covariancematematik-istatistik-optimizasyon
A fundamental statistical measure that shows how two variables change together.
🌉Cross-Attentionderin-ogrenme
An attention mechanism that allows one representation set to draw context from another representation set.
🌐Cross-Corpus Emotion Recognitionses-konusma-audio-ai
A problem focused on generalizing an emotion model learned on one dataset to new datasets recorded under different conditions.
🏁Cross-Encoder Rerankingdogal-dil-isleme
A second-stage retrieval model that jointly encodes query and candidate document to estimate relevance more precisely.
🎯Cross-Entropy Lossmatematik-istatistik-optimizasyon
A core classification loss that measures the mismatch between the true distribution and the model’s predicted probability distribution.
✨Curated Zoneveri-muhendisligi-ve-ai-altyapisi
The data lake layer where data has been cleaned, structured, and made more suitable for analytical use.
🏷️Custom Keyword Spottingses-konusma-audio-ai
An approach focused on designing voice-trigger systems that detect brand-, organization-, or application-specific terms and phrases.
✂️CutMixderin-ogrenme
A visual regularization technique that mixes image regions and labels together to improve robustness.
🕛Cutoff Timeveri-muhendisligi-ve-ai-altyapisi
A time boundary that determines until what moment a batch job will accept records for a given data period.

D

🕸️DAGveri-muhendisligi-ve-ai-altyapisi
A core orchestration structure that models data processing tasks as a directed acyclic dependency graph.
🧭DBSCANmakine-ogrenmesi
A clustering algorithm that identifies clusters and noise points together using a density-based approach.
🏫Dartmouth Conferenceyapay-zeka-temelleri
The 1956 meeting widely regarded as the historical turning point where AI began to take shape as a distinct research field.
📊Dashboard Lineageveri-muhendisligi-ve-ai-altyapisi
A trace structure that shows which datasets, queries, and transformations feed the metrics and visuals inside a dashboard.
🧩Data Associationbilgisayarli-goru
The problem of matching object observations across frames to the same physical target.
🖼️Data Augmentationderin-ogrenme
A regularization approach that improves generalization by expanding training data through meaningful transformations.
📚Data Catalogveri-bilimi-ve-veri-yonetimi
A centralized catalog structure that presents definitions, ownership, usage, and discovery information for enterprise data assets.
📥Data Collectionveri-bilimi-ve-veri-yonetimi
The systematic process of acquiring data for analysis, reporting, and modeling workflows.
⏱️Data Collection SLAveri-bilimi-ve-veri-yonetimi
An operational service-level framework that defines timeliness, completeness, and availability standards for data flows.
📜Data Contract Enforcementveri-muhendisligi-ve-ai-altyapisi
An approach in which schema, quality, and delivery expectations are not only defined, but actively enforced by the system.
📄Data Contractsveri-bilimi-ve-veri-yonetimi
An agreement approach that explicitly defines schema, quality, and delivery expectations between data producers and consumers.
🏛️Data Governanceveri-bilimi-ve-veri-yonetimi
The enterprise framework for managing data through ownership, quality, access, usage, and control principles.
🌊Data Lakeveri-muhendisligi-ve-ai-altyapisi
A storage layer where structured and unstructured data is kept in raw or lightly processed form at scale.
🛡️Data Leakageyapay-zeka-temelleri
A situation where model performance appears misleadingly strong because it has learned information during training that would not be available in real use.
🗂️Data Lifecycle Tieringveri-muhendisligi-ve-ai-altyapisi
An approach in which data is moved across storage tiers as its access frequency, age, and business value change.
🔍Data Lineageveri-bilimi-ve-veri-yonetimi
The visible trace of all movements and transformations a data element undergoes from source to report or model.
📉Data Minimizationveri-bilimi-ve-veri-yonetimi
The principle of collecting and processing only the data that is truly necessary for a defined purpose.
📡Data Observabilityveri-bilimi-ve-veri-yonetimi
A monitoring approach that aims to detect data issues, anomalies, and silent quality degradation early.
👤Data Ownershipveri-bilimi-ve-veri-yonetimi
The principle that defines which business or technical role is responsible for the quality, definition, and use of specific data domains.
🛤️Data Pipelineveri-muhendisligi-ve-ai-altyapisi
A processing chain that reliably moves data from a source, through transformations, into one or more target systems.
📦Data Product Lineageveri-muhendisligi-ve-ai-altyapisi
A trace structure showing which sources feed a data product, how it is produced, and which consumers it serves.
🔬Data Profilingveri-bilimi-ve-veri-yonetimi
The process of systematically examining a dataset’s content, distribution, missingness, uniqueness, and rule violations.
🪪Data Provenanceveri-muhendisligi-ve-ai-altyapisi
A source-reliability perspective that describes the origin, creation conditions, and processing history of a data element.
🗂️Data Sourceveri-bilimi-ve-veri-yonetimi
The system, platform, or operational touchpoint where data is generated, stored, or retrieved.
🧑‍💼Data Stewardshipveri-bilimi-ve-veri-yonetimi
An operational approach in which specific data domains are actively stewarded for definition, quality, and appropriate use.
🔠Data Type Mismatchveri-bilimi-ve-veri-yonetimi
A problem arising when the expected data type of a field differs from the actual stored content type.
🏢Data Warehouseveri-muhendisligi-ve-ai-altyapisi
A structured, integrated, query-optimized data storage environment built for reporting, analytics, and decision support.
🗃️Datasetyapay-zeka-temelleri
An organized collection of data that enables a model to be trained, evaluated, or tested.
🗺️Dataset Dependency Mapveri-muhendisligi-ve-ai-altyapisi
A mapping structure that systematically shows dependency relationships among datasets.
🛡️De-identificationdogal-dil-isleme
The process of masking personal or sensitive information in text to enable safer processing.
🌳Decision Tree Classifiermakine-ogrenmesi
A tree-based classification model that produces class decisions by recursively splitting data through sequential rules.
📝Decoder-Only Transformerderin-ogrenme
A modern large-language-model architecture that generates autoregressively by predicting the next token.
🕸️Deep Learningyapay-zeka-temelleri
A modern machine learning approach that learns hierarchical representations from data using multi-layer neural networks.
🏗️Deep Neural Networkderin-ogrenme
A general neural network structure that learns hierarchical features through multiple hidden layers.
🧠DeepSORTbilgisayarli-goru
A tracking system that strengthens the SORT approach with appearance embeddings to improve identity stability.
🌀Deformable DETRbilgisayarli-goru
An approach in transformer-based detection that makes attention computation more selective, improving convergence speed and small-object performance.
🧼Denoising Autoencoderderin-ogrenme
A type of autoencoder that learns more robust representations by reconstructing clean outputs from corrupted inputs.
📚Dense Passage Retrievaldogal-dil-isleme
A retrieval method that maps queries and passages into dense vectors to find relevant passages within documents.
🧲Dense Retrievaldogal-dil-isleme
A retrieval approach that performs semantic matching by representing queries and documents in a dense vector space.
🔗Dependency Managementveri-muhendisligi-ve-ai-altyapisi
The process of managing the dependencies among tasks, datasets, and execution orders within a data workflow.
🔗Dependency Resolutionveri-muhendisligi-ve-ai-altyapisi
The process of determining in what order and under what conditions tasks and data assets in a workflow should execute.
📱Depthwise Separable Convolutionderin-ogrenme
An efficient convolution structure that reduces CNN computation by separating spatial and channel transformations.
🏠Dereverberationses-konusma-audio-ai
An audio processing task focused on reducing the degrading effect of room reverberation on speech signals.
📈Derivativematematik-istatistik-optimizasyon
A fundamental mathematical concept that measures the rate of change and slope of a function at a given point.
🧪Derived Featureveri-bilimi-ve-veri-yonetimi
A new feature computed or transformed from existing fields rather than directly coming from raw data.
🔷Determinantmatematik-istatistik-optimizasyon
A core linear algebra quantity that summarizes a matrix’s volume scaling effect and whether it is invertible.
📊Diarization Error Rateses-konusma-audio-ai
A core evaluation metric that summarizes segmentation, identity, and overlap errors in speaker diarization systems.
✂️Diarization Resegmentationses-konusma-audio-ai
A process that refines initial diarization output afterward to improve speaker boundaries and segment accuracy.
📏Dice Coefficientbilgisayarli-goru
A segmentation-focused evaluation metric that measures overlap between predicted and ground-truth masks.
🔐Differential Privacyveri-bilimi-ve-veri-yonetimi
A mathematical privacy framework that limits the extent to which any single individual’s data can affect published results.
🌫️Diffusion-Based Audio Enhancementses-konusma-audio-ai
A next-generation generative enhancement approach that models audio restoration through iterative denoising.
🌫️Diffusion-Based Synthetic Dataveri-bilimi-ve-veri-yonetimi
A modern synthetic data generation approach that reconstructs data distributions through noise injection and reverse sampling.
🕳️Dilated Convolutionderin-ogrenme
A convolution technique that enlarges the receptive field by inserting gaps between filter elements.
📐Dimensional Modelingveri-muhendisligi-ve-ai-altyapisi
A modeling approach that organizes analytical data structures around facts and dimensions.
📉Dimensionality Reductionyapay-zeka-temelleri
An approach that reduces the number of variables representing data while preserving as much useful information as possible.
⚖️Direct Preference Optimizationuretken-yapay-zeka-ve-llm
A simpler alignment approach that learns directly from preference pairs.
↗️Directional Derivativematematik-istatistik-optimizasyon
A derivative concept that measures how fast a function changes in a specific direction.
🎨Dirichlet Distributionmatematik-istatistik-optimizasyon
A multidimensional probability distribution used to model the probabilities of multiple categories jointly.
📏Distance Metricyapay-zeka-temelleri
A mathematical function that numerically measures the difference or separation between two data points.
🧠Document Parsingbilgisayarli-goru
A process that decomposes a document into text, structure, fields, and hierarchy to produce a machine-processable representation.
📄Document-Level Machine Translationdogal-dil-isleme
An approach that improves consistency by translating sentences within broader document context rather than independently.
🎲Domain Randomizationveri-bilimi-ve-veri-yonetimi
An approach that varies environmental factors in synthetic data generation to make models more robust to the real world.
🏥Domain-Adaptive Fine-Tuninguretken-yapay-zeka-ve-llm
An approach that adapts a model to the terminology and usage style of specific domains such as law, healthcare, or finance.
🏥Domain-Specific Embeddingsdogal-dil-isleme
Representation structures adapted to the terminology of specific domains such as law, healthcare, or finance rather than general language.
✖️Dot Productmatematik-istatistik-optimizasyon
A core linear algebra operation that measures alignment and magnitude interaction between two vectors.
⚠️Downstream Breakage Riskveri-muhendisligi-ve-ai-altyapisi
A risk measure describing the likelihood that a change in a data asset will cause breakage in connected reports, models, or services.
🪂Dropoutderin-ogrenme
A regularization technique that reduces overfitting by temporarily disabling some neurons during training.
🪞Duplicate Recordveri-bilimi-ve-veri-yonetimi
A repeated data record that represents the same real-world entity or event more than once.
⏱️Duration Modeling in TTSses-konusma-audio-ai
A modeling layer that determines how long each phoneme or unit should be spoken in speech synthesis and strongly affects fluency.

E

📡ECAPA-TDNNses-konusma-audio-ai
An advanced architecture that uses channel attention and multi-scale temporal structure to improve speaker embedding quality.
☁️ELTveri-muhendisligi-ve-ai-altyapisi
A modern approach in which data is loaded into the target platform first, and transformations are performed later inside the storage or compute layer.
📉ELUderin-ogrenme
An activation function that uses smooth exponential behavior in the negative region to encourage a more balanced activation distribution.
🔄ETLveri-muhendisligi-ve-ai-altyapisi
A classic data integration approach in which data is extracted from source systems, transformed, and then loaded into a target analytical environment.
⏹️Early Stoppingderin-ogrenme
A strategy that prevents overfitting by stopping training when validation performance begins to deteriorate.
🚚Earth Mover’s Distancematematik-istatistik-optimizasyon
A distance concept that measures how much mass must be moved to transform one distribution into another.
🔇Echo Cancellationses-konusma-audio-ai
A real-time processing task focused on preventing speaker output from looping back into the microphone and degrading communication.
🪒Edge Detectionbilgisayarli-goru
A classical feature extraction task that summarizes image structure by finding boundaries with strong intensity changes.
📐Effect Sizematematik-istatistik-optimizasyon
A measure that captures not just whether an effect is significant, but how large it actually is.
🧭Eigenvalue and Eigenvectormatematik-istatistik-optimizasyon
Vectors that preserve their direction under a linear transformation, along with the associated scaling factors.
🧵Elastic Net Regressionmakine-ogrenmesi
A regression method that combines L1 and L2 regularization to provide both coefficient shrinkage and partial feature selection.
⭕Elliptic Envelopemakine-ogrenmesi
A statistical anomaly method that detects outliers by assuming the data follows an approximately elliptical distribution.
📍Embeddingyapay-zeka-temelleri
A learned dense vector representation that carries the meaning of a word, document, image, or another entity.
🏷️Embedding Versioningveri-muhendisligi-ve-ai-altyapisi
An approach for managing different embedding models or updated embedding-generation processes through versions.
🌟Emergent Capabilitiesuretken-yapay-zeka-ve-llm
Task behaviors that appear significantly stronger once a model reaches a certain scale.
🔬Emotion Cause Analysisdogal-dil-isleme
A task focused not only on identifying the emotion in text but also on finding the part that triggered it.
🎭Emotion Classificationdogal-dil-isleme
A task that classifies text into finer-grained emotional categories such as joy, anger, fear, or sadness.
🔄Encoder-Decoder RNNderin-ogrenme
A classical sequential architecture that compresses an input sequence into context and generates an output sequence from it.
🔀Encoder-Decoder Transformerderin-ogrenme
The classical Transformer architecture that encodes an input sequence and contextually generates an output sequence.
📚Encoder-Only Transformerderin-ogrenme
A Transformer architecture focused on contextual representation learning and used mainly for understanding tasks.
🔢Encodingveri-bilimi-ve-veri-yonetimi
The process of converting categorical data into numerical representations that models can process.
🔗End-to-End ASRses-konusma-audio-ai
An approach that performs speech-to-text conversion with a single unified network instead of separate acoustic and language models.
🧠End-to-End Neural Diarizationses-konusma-audio-ai
A modern diarization approach that learns segmentation, speaker separation, and timing decisions in a more unified way.
🔗Entity Linkingdogal-dil-isleme
The task of matching an entity mention in text to the correct identity or concept in a knowledge base.
🧩Entity Resolutionveri-bilimi-ve-veri-yonetimi
The process of determining whether different records actually refer to the same real-world entity.
🌫️Entropymatematik-istatistik-optimizasyon
A fundamental information-theoretic concept that measures uncertainty, disorder, or information content in a probability distribution.
🌪️Estimator Variancematematik-istatistik-optimizasyon
A measure of how much a method’s results vary across different samples.
🧷Event Coreferencedogal-dil-isleme
The task of determining whether event mentions across sentences or documents refer to the same underlying event.
📌Event Extractiondogal-dil-isleme
The task of extracting events, triggers, and participating entities from text in a structured way.
📚Event Schema Registryveri-muhendisligi-ve-ai-altyapisi
A structure in which event schemas are centrally stored and their evolution is managed in stream-based systems.
🕒Event Timeveri-muhendisligi-ve-ai-altyapisi
A time concept expressing when an event actually occurred, independent of when it reached the system.
📍Event Trackingveri-bilimi-ve-veri-yonetimi
A tracking approach that records user or system behaviors as discrete events.
1️⃣Exactly-Once Semanticsveri-muhendisligi-ve-ai-altyapisi
A processing model that aims to guarantee each data event is logically handled exactly once by the system.
📌Expected Valuematematik-istatistik-optimizasyon
A measure indicating the long-run average value a random variable is expected to approach.
📚Expert Systemyapay-zeka-temelleri
A classical AI approach that models domain expertise through rules and a knowledge base to perform inference.
💥Exploding Gradientsderin-ogrenme
An optimization problem in which gradients grow excessively during backpropagation and destabilize training.
🧭Exploration-Exploitation Trade-offyapay-zeka-temelleri
The balance problem between trying new options to gain information and using already known good options.
⏳Exponential Distributionmatematik-istatistik-optimizasyon
A continuous distribution used to model the waiting time until an event occurs.
📈Exponential Smoothingmakine-ogrenmesi
A time series method that assigns weighted importance to past observations and can model level, trend, and seasonality.
⚠️Exposure Biasderin-ogrenme
The problem in which a model trained on correct past context must face its own imperfect history during inference.
🎭Expressive Speech Synthesisses-konusma-audio-ai
A TTS approach focused on generating not only correct words but also appropriate style, tone, and emotional effect.
📍Extractive Question Answeringdogal-dil-isleme
A question answering approach that selects the answer as a span from a provided passage.
✂️Extractive Summarizationdogal-dil-isleme
A content-preserving summarization approach that creates summaries by selecting important sentences from the source text.

F

📐Face Alignmentbilgisayarli-goru
A process that places the face into a common geometric reference frame to make downstream analysis more consistent.
🛡️Face Anti-Spoofingbilgisayarli-goru
A security task that aims to distinguish attacks such as printed photos, replay screens, or masks from genuine face access.
🙂Face Detectionbilgisayarli-goru
A core face analysis task focused on locating face regions in an image or video.
🧬Face Embedding Spacebilgisayarli-goru
A discriminative representation space that positions face images according to identity similarity.
🧠Face Recognitionbilgisayarli-goru
A task focused on distinguishing individuals by producing identity-like discriminative representations from face images.
✅Face Verificationbilgisayarli-goru
A binary decision problem that evaluates whether two face images belong to the same person.
🎭Facial Expression Recognitionbilgisayarli-goru
A task focused on predicting emotional or behavioral expression types from facial muscle movement patterns.
📍Facial Landmark Detectionbilgisayarli-goru
A fine-grained vision task that identifies key points of face anatomy such as eyes, nose, mouth, and jaw.
🧭Factual Consistency Evaluationdogal-dil-isleme
An evaluation dimension that measures how consistent a generated summary or answer is with the facts in the source content.
📌Factualityuretken-yapay-zeka-ve-llm
A quality dimension describing how well generated content aligns with real-world facts, source data, or verifiable truth.
🚫False Trigger Rateses-konusma-audio-ai
A critical quality metric expressing how often keyword systems activate incorrectly.
🧬FastText Embeddingsdogal-dil-isleme
An embedding method that represents words through sub-character pieces and behaves more robustly on rare and derived forms.
🧱Featureyapay-zeka-temelleri
A measurable attribute or input variable that describes a data instance from the model’s perspective.
✅Feature Consistency Checkveri-muhendisligi-ve-ai-altyapisi
A validation process that verifies whether training-side and serving-side feature values are produced with the same logic and definition.
🗑️Feature Deprecation Policyveri-muhendisligi-ve-ai-altyapisi
A policy that governs the controlled retirement of feature definitions that are no longer recommended or supported.
🔧Feature Engineeringyapay-zeka-temelleri
The process of creating more meaningful, discriminative, and useful features from raw data for a model.
🧮Feature Hashingveri-bilimi-ve-veri-yonetimi
A method that maps features into a fixed-dimensional space using hash functions to provide scalable representation.
🏗️Feature Hierarchyderin-ogrenme
The structure in which representations become increasingly abstract from lower to higher layers.
🗺️Feature Mapderin-ogrenme
The spatial activation representation produced by a convolution layer through specific filters.
🗻Feature Pyramid Networkderin-ogrenme
An architectural design that combines visual information across scales to improve multi-scale object understanding.
📚Feature Registryveri-muhendisligi-ve-ai-altyapisi
A registry layer where feature definitions, versions, ownership, and usage states are centrally maintained.
🎯Feature Selectionveri-bilimi-ve-veri-yonetimi
The process of selecting the most informative variables for a model in order to reduce noise, cost, and complexity.
🔌Feature Serving APIveri-muhendisligi-ve-ai-altyapisi
A service layer that delivers the required features through a standardized interface during live prediction.
🏪Feature Storeveri-muhendisligi-ve-ai-altyapisi
An infrastructure layer where machine learning features are centrally managed with reuse and training-serving consistency.
🏷️Feature Versioningveri-muhendisligi-ve-ai-altyapisi
An approach for managing changes in feature definitions as traceable versions over time.
➡️Feedforward Neural Networkderin-ogrenme
The classical family of neural networks in which information flows one-way from input to output.
🧪Few-Shot Audio Classificationses-konusma-audio-ai
A low-data learning approach aimed at recognizing new audio events or classes from very few examples.
🧪Few-Shot Image Classificationbilgisayarli-goru
A learning approach that aims to distinguish new visual categories when only a few examples per class are available.
🧪Few-Shot Promptingdogal-dil-isleme
A prompting technique that adapts model behavior by guiding it with example input-output pairs.
✂️File Pruningveri-muhendisligi-ve-ai-altyapisi
An optimization technique that improves data lake performance by avoiding scans of unnecessary files during queries.
🔬Fine-Grained Image Classificationbilgisayarli-goru
A high-resolution classification problem focused on distinguishing highly similar subcategories.
🔬Fisher Informationmatematik-istatistik-optimizasyon
A statistical quantity that measures how much precise information the observed data carries about a model parameter.
🎯Focal Lossmatematik-istatistik-optimizasyon
A classification loss that reduces the impact of easy examples and focuses more on hard or rare ones.
⏱️Forced Alignmentses-konusma-audio-ai
A process that aligns existing text with speech in time to produce word- or phoneme-level correspondence.
📈Formant Analysisses-konusma-audio-ai
A classical analysis approach that examines resonance regions in speech to extract phonetic and speaker-related information.
🪄Fuzzy Matchingveri-bilimi-ve-veri-yonetimi
A matching approach that uses similarity-based rules to find near-matching records instead of exact matches.

G

🧠GAN-Based Synthetic Dataveri-bilimi-ve-veri-yonetimi
A synthetic data approach based on generating new data samples similar to the real distribution using generative adversarial networks.
🌊GELU Activationderin-ogrenme
A modern activation function that transforms inputs with probabilistic smoothness rather than a hard threshold.
⚙️GRUderin-ogrenme
A recurrent unit that learns sequence dependencies through a simpler gating structure than LSTM.
🟨Gamma Distributionmatematik-istatistik-optimizasyon
A flexible distribution used to model positive continuous quantities and waiting times for multiple events.
🚪Gated Linear Unitderin-ogrenme
An activation-like structure that filters linear signals through a gating mechanism to enable more selective information flow.
🔔Gaussian Mixture Modelmakine-ogrenmesi
A probabilistic model that assumes the data is generated from a mixture of multiple Gaussian distributions.
👀Gaze Estimationbilgisayarli-goru
A fine-grained face analysis task focused on estimating where a person is looking from eye direction.
📈Generalizationyapay-zeka-temelleri
The ability of a model to produce accurate, stable, and reliable results on examples it did not see during training.
✨Generative AIyapay-zeka-temelleri
A class of AI systems capable of generating new content such as text, images, audio, video, or code.
✨Generative Modeluretken-yapay-zeka-ve-llm
A family of models that can generate new samples rather than only predicting labels.
💬Generative Question Answeringdogal-dil-isleme
A QA approach that generates answers as free text, offering more natural but potentially riskier responses.
📐Geometric Transformationbilgisayarli-goru
A family of operations that rearranges image coordinates to apply scaling, rotation, translation, and perspective changes.
🌍GloVedogal-dil-isleme
An embedding method that produces dense word vectors using global word co-occurrence statistics.
📚Glossary Alignmentveri-muhendisligi-ve-ai-altyapisi
The process of aligning business glossary terms with technical data assets in a semantically consistent way.
🧭Gradientmatematik-istatistik-optimizasyon
A vector containing the partial derivatives of a multivariable function, indicating direction and magnitude of change.
🚀Gradient Boostingmakine-ogrenmesi
A boosting-based ensemble method that builds strong predictions by sequentially reducing the errors of previous models.
✅Gradient Checkingderin-ogrenme
A debugging technique that validates analytical gradients by comparing them with numerical approximations.
✂️Gradient Clippingmatematik-istatistik-optimizasyon
A technique that limits gradient magnitude to prevent excessively large gradients from destabilizing training.
⛰️Gradient Descentmatematik-istatistik-optimizasyon
A fundamental optimization method that updates parameters in the opposite direction of the gradient to minimize a loss function.
🌊Gradient Flowderin-ogrenme
A core training-dynamics concept describing how effectively the learning signal moves across network layers.
📉Gradient Noise Scalederin-ogrenme
A training-dynamics measure that characterizes how noisy gradient estimates are in stochastic optimization.
🎯Graph Attention Networkderin-ogrenme
A GNN architecture that combines neighboring nodes with learned attention weights rather than treating them equally.
🕸️Graph Classificationderin-ogrenme
A graph learning task focused on assigning a single label to the entire graph.
🕸️Graph Convolutional Networkderin-ogrenme
A foundational GNN architecture that learns representations over graphs by using neighborhood information.
🧬Graph Isomorphism Networkderin-ogrenme
A GNN architecture designed to strengthen the theoretical power of distinguishing graph structures.
📦Graph Poolingderin-ogrenme
A GNN operation that aims to compress node information into more compact and task-relevant representations.
🌐GraphSAGEderin-ogrenme
A GNN method that makes representation learning scalable on large graphs through neighborhood sampling.
🔲Grid Searchmakine-ogrenmesi
A method that searches for the best model by systematically trying predefined hyperparameter combinations.
✅Ground Truthveri-bilimi-ve-veri-yonetimi
The trusted reference label or verification information considered correct for a data instance.

H

🧭HDBSCANmakine-ogrenmesi
An advanced clustering method that detects clusters with varying density levels through a hierarchical density-based approach.
🕸️HNSW Indexveri-muhendisligi-ve-ai-altyapisi
An indexing method that uses a hierarchical graph structure for fast approximate neighbor search in high-dimensional vectors.
📶HOG Featuresbilgisayarli-goru
A classical feature extraction approach that represents shape and edge structure through local gradient orientation distributions.
🌫️Hallucinationuretken-yapay-zeka-ve-llm
The phenomenon in which a model generates fluent but unsupported or incorrect content.
✍️Handwriting Recognitionbilgisayarli-goru
An OCR subtask focused on converting handwritten content, which is far more variable than printed text, into machine-readable text.
⛏️Hard Negative Miningdogal-dil-isleme
A training strategy that improves retrieval and matching quality by providing semantically confusing hard negatives rather than easy negatives.
📱Hard-Swish Activationderin-ogrenme
An efficient activation function designed to approximate Swish-like behavior at lower computational cost.
🧭Head Pose Estimationbilgisayarli-goru
A geometric analysis task that estimates the orientation of the face or head in space through angle values.
🏔️Hessian Matrixmatematik-istatistik-optimizasyon
A matrix of second-order derivatives that helps describe the curvature of a function.
📐Hessian-Vector Productderin-ogrenme
A computational technique that accesses second-order information without explicitly forming the full Hessian matrix.
🧩Heterogeneous Graph Neural Networkderin-ogrenme
An advanced GNN architecture capable of modeling different node and relation types within the same graph.
🧩Heuristicyapay-zeka-temelleri
A guiding approach that may not guarantee the optimal solution but helps reach good solutions faster in practice.
📏Hidden Layer Widthderin-ogrenme
An architectural concept referring to the number of neurons in a layer and directly affecting model capacity.
🎲Hidden Markov Modelmakine-ogrenmesi
A sequential probabilistic structure that models hidden state transitions behind observable outputs.
🧠Hidden Statederin-ogrenme
An internal representation vector in sequence models that carries past information and is updated over time.
🌲Hierarchical Clusteringmakine-ogrenmesi
A clustering approach that represents similarity among data points through a tree-like hierarchical structure.
🌲Hierarchical Image Classificationbilgisayarli-goru
A multi-level visual classification problem in which class labels are organized in a parent-child taxonomy.
🌲Hierarchical Text Classificationdogal-dil-isleme
A classification problem in which labels are organized in a parent-child hierarchy rather than a flat list.
🪓Hinge Lossmatematik-istatistik-optimizasyon
A loss function used especially in support vector machines that aims to create a safe margin between classes.
📊Histogram Equalizationbilgisayarli-goru
A classical enhancement technique that redistributes intensity values to improve image contrast.
⚖️Huber Lossmatematik-istatistik-optimizasyon
A hybrid loss function that balances MSE and MAE behavior and is more robust to outliers.
🛡️Huber Regressionmakine-ogrenmesi
A robust regression method that is more resistant to outliers than ordinary least squares.
🧮Hungarian Assignment for Trackingbilgisayarli-goru
An optimization step that preserves identity continuity by matching detections with existing tracks at minimum cost.
⚖️Hybrid Retrievaldogal-dil-isleme
An approach that combines sparse and dense retrieval signals to provide more balanced search quality.
🔀Hybrid Searchveri-muhendisligi-ve-ai-altyapisi
An approach that combines semantic vector search with keyword-based and filter-based classical retrieval techniques.
🏎️Hyperbandmakine-ogrenmesi
An optimization method that uses dynamic resource allocation to eliminate poor hyperparameter candidates early.

I

4️⃣INT4 Quantizationuretken-yapay-zeka-ve-llm
An aggressive quantization approach that reduces the model to 4-bit precision for much lower memory cost.
8️⃣INT8 Quantizationuretken-yapay-zeka-ve-llm
A common quantization form that reduces weights and sometimes activations to 8-bit precision for balanced efficiency and quality.
♻️Idempotencyveri-muhendisligi-ve-ai-altyapisi
The property of producing a stable, non-duplicated result even when the same operation is run multiple times.
🖼️Image Augmentationbilgisayarli-goru
A data-driven technique that improves model generalization by diversifying training data through transformations.
📝Image Captioningbilgisayarli-goru
The task of expressing the content of an image in fluent and meaningful natural language.
🔧Image Deblurringbilgisayarli-goru
A restoration task that aims to recover visual information by reducing blur caused by motion, focus error, or camera shake.
🧼Image Denoisingbilgisayarli-goru
The process of improving image quality by reducing noise caused by sensors, compression, or transmission.
⚖️Image Normalizationbilgisayarli-goru
A preprocessing step that brings pixel values into a defined range or distribution to make model training more stable.
📐Image Registrationbilgisayarli-goru
The process of aligning images from different times, viewpoints, or sensors within a common coordinate system.
🔍Image Super-Resolutionbilgisayarli-goru
A restoration approach focused on generating more detailed high-resolution images from low-resolution inputs.
🧲Image-Text Contrastive Learningbilgisayarli-goru
An approach that learns multimodal representations by bringing related image-text pairs together and pushing unrelated pairs apart in a shared space.
🔎Image-Text Retrievalbilgisayarli-goru
A task that retrieves relevant images from text or relevant text from images through a shared multimodal representation space.
🎯Imbalance-Aware Calibrationveri-bilimi-ve-veri-yonetimi
An approach that helps model probabilities reflect true risk levels more accurately under class imbalance.
💥Impact Analysisveri-muhendisligi-ve-ai-altyapisi
The process of assessing in advance which reports, models, tables, or workflows may be affected by a data change.
🧠Implicit Differentiationderin-ogrenme
An approach for computing derivatives through solutions or equilibrium conditions that are not written explicitly.
👆Implicit Feedback Recommendationmakine-ogrenmesi
A recommendation approach that relies on behavioral signals such as clicks, views, and purchases instead of explicit ratings.
🩹Imputationveri-bilimi-ve-veri-yonetimi
The process of filling missing observations using statistical, rule-based, or model-driven methods.
🧠In-Context Learningdogal-dil-isleme
The ability of a model to adapt task behavior from examples in context without updating its parameters.
🪢Independencematematik-istatistik-optimizasyon
A concept describing the case where the occurrence of one event or variable does not affect the probability of another.
🎛️Independent Component Analysismakine-ogrenmesi
A dimensionality reduction and separation method that aims to decompose mixed signals into statistically independent components.
🧭Inductive Biasderin-ogrenme
The structural tendency that determines which kinds of patterns a model is naturally more likely to learn.
🚀Inferenceyapay-zeka-temelleri
The stage in which a trained model performs prediction or generation on new data in real-world use.
🌱Information Gainmatematik-istatistik-optimizasyon
An information-theoretic concept that measures how much uncertainty a feature reduces, especially in decision trees.
🎭Instance Segmentationbilgisayarli-goru
A task that distinguishes individual objects of the same class and produces a pixel mask for each one.
📋Instruction Followingdogal-dil-isleme
The ability of a model to reliably follow task instructions expressed in natural language.
📋Instruction Modeluretken-yapay-zeka-ve-llm
A version of a general language model adapted to follow task instructions more effectively.
📋Instruction Tuningdogal-dil-isleme
A fine-tuning approach that adapts a language model to respond better to natural language task instructions.
🎛️Instrumentation Designveri-bilimi-ve-veri-yonetimi
A design approach that defines which events and fields should be recorded, and how, in order to measure product, process, or system behavior correctly.
🤖Intelligent Agentyapay-zeka-temelleri
An autonomous or semi-autonomous system that perceives its environment and selects actions to achieve its goals.
🎯Intent Classificationdogal-dil-isleme
A task focused on predicting what purpose or action intent a user utterance represents.
🤝Inter-Annotator Agreementveri-bilimi-ve-veri-yonetimi
A quality measure indicating how consistently different annotators make similar decisions on the same data.
🔗Interaction Featureveri-bilimi-ve-veri-yonetimi
A combined variable created to capture the joint effect of two or more features.
↩️Inverse Matrixmatematik-istatistik-optimizasyon
A matrix that reverses a linear transformation and is defined only for full-rank matrices.
🌲Isolation Forestmakine-ogrenmesi
An anomaly detection method based on the assumption that anomalous instances are easier to isolate.
🗺️Isomapmakine-ogrenmesi
A nonlinear dimensionality reduction method that seeks to preserve manifold structure through approximate geodesic distances.

J

🧾Jacobianmatematik-istatistik-optimizasyon
A matrix structure that carries derivative information for vector-valued functions.
📐Jacobian Matrixderin-ogrenme
A matrix representing the derivative structure of vector-valued functions and playing an important role in multidimensional backpropagation.
🔀Jensen-Shannon Divergencematematik-istatistik-optimizasyon
An information-theoretic divergence measure that compares two distributions in a more symmetric and stable way.
⛓️Job Chainingveri-muhendisligi-ve-ai-altyapisi
An execution model in which batch jobs trigger one another sequentially based on output-input relationships.
⏰Job Schedulerveri-muhendisligi-ve-ai-altyapisi
A system component that governs when and under what conditions batch or hybrid jobs should run.

K

🔁K-Fold Cross Validationmatematik-istatistik-optimizasyon
A method that repeatedly evaluates a model across different data folds to provide a more reliable estimate of performance.
🎯K-Meansmakine-ogrenmesi
One of the most common clustering algorithms, which partitions data points into k clusters based on distance to centroids.
🧭K-Nearest Neighbors Classifiermakine-ogrenmesi
An instance-based classification method that labels a sample according to the classes of its nearest neighbors in feature space.
📡KL Divergencematematik-istatistik-optimizasyon
A directional divergence measure that quantifies how one probability distribution differs from another.
⚙️KV Cacheuretken-yapay-zeka-ve-llm
A mechanism that stores previous attention computations to reduce repeated work in autoregressive generation.
📈Kalman Filter Trackingbilgisayarli-goru
A classical approach that stabilizes tracking by predicting an object’s future position through a motion model.
💾Key-Value Cachederin-ogrenme
A mechanism that speeds up autoregressive Transformer inference by storing previous attention representations.
🔑Key-Value Extractionbilgisayarli-goru
A task that matches field names with their corresponding values in a document to create structured data.
🔑Keyphrase Extractiondogal-dil-isleme
The task of automatically identifying the key terms and phrases that best represent a text.
📌Keypoint Detectionbilgisayarli-goru
An operation that finds distinctive and repeatable local points in an image to support matching and alignment tasks.
🏛️Knowledge Baseyapay-zeka-temelleri
A structured repository that stores the facts, rules, relationships, and domain knowledge used by a system.
📦Knowledge Distillation in Visionbilgisayarli-goru
An approach for transferring knowledge from a large, powerful vision model into a smaller and more efficient one.
🗂️Knowledge Representationyapay-zeka-temelleri
The approach of transforming facts, relationships, and rules about the world into machine-processable structures.
📊Kurtosismatematik-istatistik-optimizasyon
A measure that summarizes tail heaviness and the tendency of a distribution to produce outliers.
👥k-Anonymityveri-bilimi-ve-veri-yonetimi
A privacy protection model that aims to make each individual indistinguishable from at least k others.

L

🧠LSTMderin-ogrenme
An advanced recurrent architecture that uses gating mechanisms to learn long-term dependencies.
🌳Label Ontologyveri-bilimi-ve-veri-yonetimi
A classification framework that defines the hierarchical, relational, and conceptual structure of labels.
🏷️Label Smoothingmatematik-istatistik-optimizasyon
A loss-related improvement technique that softens target labels to reduce overconfidence in the model.
📘Labeling Guidelineveri-bilimi-ve-veri-yonetimi
A formal instruction document defining the rules, examples, and exceptions to be used during labeling.
⏮️Lag Featureveri-bilimi-ve-veri-yonetimi
A type of feature that brings time-dependent patterns into the model using values from previous time steps.
🪝Lagrange Multipliersmatematik-istatistik-optimizasyon
A method used in constrained optimization to balance the objective function with the imposed constraints.
🏞️Lakehouseveri-muhendisligi-ve-ai-altyapisi
A modern architectural approach that combines the flexibility of data lakes with the manageability and performance characteristics of warehouses.
📚Language Model Fusion in ASRses-konusma-audio-ai
An approach that incorporates external language model knowledge to make speech recognition output more linguistically accurate.
📚Language Modelingdogal-dil-isleme
A foundational NLP problem focused on learning the probability structure of language sequences in order to predict next or missing units.
✂️Lasso Regressionmakine-ogrenmesi
An L1-based regression method that can perform both regularization and feature selection by driving coefficients to zero.
🧾Late Data Reconciliationveri-muhendisligi-ve-ai-altyapisi
A correction process that brings late-arriving data into alignment with previously produced batch outputs.
🧩Late-Interaction Embeddingsdogal-dil-isleme
A retrieval approach that matches queries and documents through token-level interaction instead of compressing each into a single vector.
🌐Latent Manifoldderin-ogrenme
The idea that meaningful low-dimensional structure of data is represented as a regular manifold in latent space.
🌌Latent Spaceyapay-zeka-temelleri
The internal representational space in which a model encodes data in a more abstract, compressed, and meaningful way.
🌈Latent Space Interpolationderin-ogrenme
A technique for exploring the continuity of learned structure by moving between points in latent representation space.
🧩Law of Total Probabilitymatematik-istatistik-optimizasyon
A fundamental rule for computing the total probability of an event by combining contributions from distinct cases.
📏Layer Normalizationderin-ogrenme
A technique that normalizes activations at the sample level and provides more stable training especially in sequence models.
🗂️Layout Analysisbilgisayarli-goru
A Document AI task that structurally separates titles, paragraphs, tables, images, and layout blocks in a document.
🚫Leakage Preventionveri-bilimi-ve-veri-yonetimi
A preprocessing discipline that prevents information unavailable at real usage time from leaking into model training.
🚧Leakage-Aware Feature Engineeringveri-bilimi-ve-veri-yonetimi
An approach to feature creation that preserves time, target, and operational usage boundaries to avoid leakage.
⚡Leaky ReLUderin-ogrenme
An activation function that leaves a small nonzero slope in the negative region to alleviate the dying ReLU problem.
🎚️Learning Rateyapay-zeka-temelleri
A core hyperparameter that determines how much model parameters change at each update step.
📘Lemmatizationdogal-dil-isleme
The process of reducing a word to its dictionary base form while considering grammatical information.
💡LightGBMmakine-ogrenmesi
A tree-based method that delivers fast and efficient boosting performance on large-scale tabular problems.
🔍Likelihoodmatematik-istatistik-optimizasyon
A statistical concept expressing how probable the observed data is under a given model parameter setting.
🕒Limited Memory AIyapay-zeka-temelleri
A type of AI that uses not only current input but also some recent observations and state information when making decisions.
📍Line Searchmatematik-istatistik-optimizasyon
An optimization step-size selection approach that determines how far to move along a chosen direction.
🧩Lineage Completenessveri-muhendisligi-ve-ai-altyapisi
A quality dimension describing how fully lineage information covers all critical steps and dependencies in the data flow.
📏Lineage Confidence Scoreveri-muhendisligi-ve-ai-altyapisi
A quality indicator that expresses the reliability level of automatically or semi-automatically inferred lineage information.
🤝Lineage Reconciliationveri-muhendisligi-ve-ai-altyapisi
The process of reconciling trace information coming from different lineage sources into a consistent view.
🔐Lineage-Driven Access Impactveri-muhendisligi-ve-ai-altyapisi
An approach that analyzes the impact of access permission changes on connected data products and consumer systems.
🔄Lineage-Metadata Syncveri-muhendisligi-ve-ai-altyapisi
A synchronization approach that keeps metadata definitions and lineage relationships consistent and up to date.
📈Linear Attentionderin-ogrenme
An approach that aims to make attention computation more scalable by reducing complexity to an approximately linear form.
📏Linear Discriminant Analysismakine-ogrenmesi
A statistical classification method that seeks linear projections that best separate classes.
📈Linear Regressionmakine-ogrenmesi
A fundamental regression algorithm that models the linear relationship between input variables and a target variable.
🔗Link Predictionderin-ogrenme
A task aimed at predicting edges that are not currently present in a graph but are likely to exist.
🧩LoRAuretken-yapay-zeka-ve-llm
A popular PEFT method that enables efficient fine-tuning by representing weight updates with low-rank matrices.
🪟Load Windowveri-muhendisligi-ve-ai-altyapisi
A boundary structure that defines which time range a load process covers and when it runs.
🔗Local Feature Matchingbilgisayarli-goru
A task that matches similar local points across images to enable alignment, registration, and 3D inference.
🔍Local Outlier Factormakine-ogrenmesi
A method that measures outlierness by comparing a point's local density to that of its neighbors.
🪵Log Lossmatematik-istatistik-optimizasyon
A loss function that measures the quality of probabilistic classification predictions and strongly penalizes wrong confidence.
📈Log-Normal Distributionmatematik-istatistik-optimizasyon
A right-skewed continuous distribution used for positive variables whose logarithm is normally distributed.
🎯Logistic Regressionmakine-ogrenmesi
A foundational classification algorithm that uses the logit function to model class probabilities.
📉Long-Tailed Recognitionbilgisayarli-goru
A problem focused on strong recognition under imbalanced data distributions where some classes are abundant and others are scarce.
📉Loss Functionyapay-zeka-temelleri
A mathematical function that quantifies the difference between model predictions and true values and guides the training process.
🌈l-Diversityveri-bilimi-ve-veri-yonetimi
A privacy model that requires sufficient diversity of sensitive values within anonymized groups.

M

📊MFCCses-konusma-audio-ai
A classical acoustic feature representation that summarizes the spectral envelope of speech in a way aligned with human hearing.
📊Machine Learningyapay-zeka-temelleri
A subfield of AI that enables systems to learn patterns from data without being explicitly programmed rule by rule.
⚖️Mann-Whitney U Testmatematik-istatistik-optimizasyon
A test used to compare two independent groups without relying on strong parametric assumptions.
🔄Markov Propertymatematik-istatistik-optimizasyon
A property stating that a system’s future depends only on its current state, not on the full past history.
🪄Mask Refinementbilgisayarli-goru
A refinement process that improves an initial segmentation output in terms of boundary quality and detail precision.
🎛️Mask-Based Speech Enhancementses-konusma-audio-ai
An approach that predicts masks over time-frequency representations to preserve speech components while suppressing noise.
🕳️Masked Language Modelingderin-ogrenme
A pretraining objective based on masking some input tokens and predicting them from context.
🧭Master Data Managementveri-bilimi-ve-veri-yonetimi
An approach for managing core enterprise entities such as customers, products, and suppliers in a unified and consistent way.
🔲Matrixmatematik-istatistik-optimizasyon
A structure of numbers arranged in rows and columns, central to data representation and transformations.
🧩Matrix Factorizationmakine-ogrenmesi
A powerful recommendation approach that generates suggestions by decomposing the user-item interaction matrix into latent factors.
🧠Maximum A Posteriori Estimation (MAP)matematik-istatistik-optimizasyon
A Bayesian estimation approach that accounts for prior knowledge while selecting parameters that explain the data.
🔍Maximum Likelihood Estimation (MLE)matematik-istatistik-optimizasyon
A fundamental statistical estimation method based on selecting the parameters that make the observed data most likely.
🧪McNemar Testmatematik-istatistik-optimizasyon
A test used to compare the error behavior of two classifiers on the same set of examples.
📏Mean Absolute Error (MAE)matematik-istatistik-optimizasyon
A regression loss function that averages the absolute differences between predictions and true values, offering greater robustness.
📈Mean Average Precisionbilgisayarli-goru
A core evaluation metric that summarizes object detection performance across classes and threshold settings.
📍Mean Shiftmakine-ogrenmesi
A clustering method that discovers clusters by seeking density modes and does not require the number of clusters in advance.
📉Mean Squared Error (MSE)matematik-istatistik-optimizasyon
A common regression loss function that averages the squared differences between predictions and true values.
📍Mean, Median, and Modematematik-istatistik-optimizasyon
Fundamental statistical measures that summarize the central tendency of a dataset from different perspectives.
🥇Medallion Architectureveri-muhendisligi-ve-ai-altyapisi
A layered data-processing model that progresses from raw data toward reliable analytical data.
🌈Mel Spectrogramses-konusma-audio-ai
A time-frequency representation that maps audio into a frequency scale closer to human auditory perception.
🧬Merge Policyveri-muhendisligi-ve-ai-altyapisi
A loading logic that defines which record should be preserved under which rule when incoming and existing records conflict.
📨Message Passing Neural Networkderin-ogrenme
A general GNN framework that updates information over graphs through message exchange among nodes.
📝Metadataveri-muhendisligi-ve-ai-altyapisi
The body of descriptive, source, usage, and technical information that exists about data.
🧷Metadata Filtering in Vector Searchveri-muhendisligi-ve-ai-altyapisi
An approach that narrows vector similarity results using additional fields such as date, source, user, or category.
📝Metadata Managementveri-bilimi-ve-veri-yonetimi
The systematic management of descriptions, sources, usage, and technical structure information about data.
🏅Metadata Quality Scoreveri-muhendisligi-ve-ai-altyapisi
A quality score used to measure the completeness, freshness, clarity, and governance maturity of metadata.
🗄️Metadata Registryveri-muhendisligi-ve-ai-altyapisi
A central registry where metadata objects are stored in a standardized, governable, and accessible form.
🕰️Metadata Versioningveri-muhendisligi-ve-ai-altyapisi
An approach that stores changes in metadata definitions as traceable versions over time.
📏Metric Learning for Visionbilgisayarli-goru
An approach that builds comparison-based visual systems by bringing similar examples closer and separating different ones in embedding space.
📦Mini-Batch Gradient Descentmatematik-istatistik-optimizasyon
A widely used optimization approach that splits training data into small batches to balance efficiency and stability.
🗜️Minimum Description Length (MDL)matematik-istatistik-optimizasyon
An information-theoretic principle stating that a good model is one that describes the data in the shortest sufficient way.
🌊Mish Activationderin-ogrenme
A modern activation function noted for its smooth shape and internally regular gradient behavior.
🕳️Missing Dataveri-bilimi-ve-veri-yonetimi
A condition in which fields expected in an observation appear as empty, null, or unknown.
🧠Mixture of Expertsuretken-yapay-zeka-ve-llm
An approach in which only relevant expert subnetworks are activated for each input to achieve scale and efficiency.
🧠Mixture-of-Experts Transformerderin-ogrenme
A Transformer approach that improves scaling efficiency by activating selected expert subnetworks rather than the full model on every input.
🧪Mixupderin-ogrenme
A data-driven regularization technique that mixes training examples and labels so the model learns smoother decision boundaries.
🌀Mode Collapseveri-bilimi-ve-veri-yonetimi
A problem in synthetic data generation where the model loses distributional diversity and produces only limited types of samples.
📐Modelyapay-zeka-temelleri
A mathematical or algorithmic structure that learns the relationship between inputs and outputs and applies it to new data.
💾Model Checkpointuretken-yapay-zeka-ve-llm
A saved model state captured at a certain stage of training and reusable later.
🤖Model Lineageveri-muhendisligi-ve-ai-altyapisi
A traceability structure that shows which data, features, code version, and training workflow produced a machine learning model.
🌪️Momentummatematik-istatistik-optimizasyon
A method that speeds up optimization by incorporating the direction of past gradient updates.
📊Monotonic Binningveri-bilimi-ve-veri-yonetimi
A feature transformation technique that bins continuous variables while preserving a monotonic relationship with the target.
🎥Multi-Camera Video Analyticsbilgisayarli-goru
An approach that jointly analyzes multiple camera streams to provide broader scene and behavior understanding.
🧩Multi-Head Attentionderin-ogrenme
A structure that runs attention in parallel across multiple subspaces to learn different types of relationships.
🪜Multi-Hop Question Answeringdogal-dil-isleme
A question answering task that requires combining multiple pieces of information to arrive at an answer.
🏷️Multi-Label Classificationmakine-ogrenmesi
A classification approach designed for problems in which a single instance can belong to multiple labels at once.
🗂️Multi-Label Image Classificationbilgisayarli-goru
A more realistic classification problem in which an image can belong to multiple classes at the same time.
🗂️Multi-Label Text Classificationdogal-dil-isleme
A classification problem in which a text can belong to multiple categories at the same time.
👥Multi-Object Trackingbilgisayarli-goru
A task that maintains both localization and identity continuity for multiple objects over time in video.
🧠Multilayer Perceptronderin-ogrenme
A fully connected neural network structure containing multiple hidden layers.
🌐Multilingual Sentence Embeddingsdogal-dil-isleme
An approach that represents sentences from different languages in a shared semantic space, enabling cross-lingual matching.
🧠Multimodal Affect Analysisses-konusma-audio-ai
An approach that performs stronger affect analysis by combining signals such as audio, text, and sometimes facial expression.
📍Multimodal Groundingbilgisayarli-goru
The process of aligning linguistic expressions with the correct region, object, or visual structure in an image.
📋Multimodal Instruction Tuningbilgisayarli-goru
A fine-tuning process that develops multimodal models capable of interpreting image and text inputs together with natural language instructions.
📚Multimodal RAG for Visionbilgisayarli-goru
An architectural approach that combines visual inputs with external knowledge sources to produce more grounded multimodal answers.
🧠Multimodal Transformeruretken-yapay-zeka-ve-llm
A model design that processes different data types such as text, images, audio, or video within a shared attention architecture.
🧪Multiple Comparison Correctionmatematik-istatistik-optimizasyon
A correction approach used to control false positives when multiple hypotheses are tested.
🎵Music Taggingses-konusma-audio-ai
A task that assigns multiple semantic tags such as genre, instrument, mood, or style to a music recording.
🔁Mutual Informationmatematik-istatistik-optimizasyon
A concept that measures how much knowing one variable reduces uncertainty about another.

N

📬Naive Bayesmakine-ogrenmesi
A fast probabilistic classification method that operates under a conditional independence assumption among features.
🏷️Named Entity Recognitiondogal-dil-isleme
The task of recognizing entity spans such as people, organizations, locations, and dates within text.
🧱Namespace Isolationveri-muhendisligi-ve-ai-altyapisi
A structure that logically separates vector collections by use case, tenant, or security boundary.
🎯Narrow AIyapay-zeka-temelleri
An AI system that performs very well on a specific task but cannot generalize that capability across broad contexts.
🧠Natural Language Inferencedogal-dil-isleme
A task that determines whether one statement entails, contradicts, or is neutral with respect to another.
📨Neighborhood Aggregationderin-ogrenme
The core GNN operation by which a node updates its representation by collecting information from its neighbors.
🪆Nested NERdogal-dil-isleme
A more complex NER problem in which one entity span can contain another entity span.
🌍Neural Machine Translationdogal-dil-isleme
A modern translation approach focused on generating target-language sequences while preserving meaning and fluency.
📐Neural Tangent Kernelderin-ogrenme
A theoretical framework that connects the training dynamics of very wide neural networks with kernel methods.
🗣️Neural Text-to-Speechses-konusma-audio-ai
A synthesis approach that uses deep learning to convert text into more natural, fluent, and human-like speech.
🌀Newton's Methodmatematik-istatistik-optimizasyon
An advanced optimization method that uses both slope and curvature information to aim for faster convergence.
🔹Node Classificationderin-ogrenme
A core GNN task focused on predicting a label for each node in a graph.
🚀Non-Autoregressive TTSses-konusma-audio-ai
A TTS approach that increases synthesis speed by generating speech more in parallel rather than step by step.
🧯Non-Maximum Suppressionbilgisayarli-goru
An operation that filters overlapping boxes produced for the same object in order to create cleaner detection output.
🧩Non-negative Matrix Factorizationmakine-ogrenmesi
A dimensionality reduction technique that produces part-based and interpretable representations in non-negative data.
🔔Normal Distributionmatematik-istatistik-optimizasyon
One of the most widely used continuous distributions in statistics, known for its bell-shaped curve.
📏Normalizationveri-bilimi-ve-veri-yonetimi
The process of bringing numerical variables to a defined scale to make them more suitable for modeling and comparison.
0️⃣Null Hypothesismatematik-istatistik-optimizasyon
The foundational starting point in hypothesis testing that assumes an observed effect is due to chance.

O

🫥Occlusion Handlingbilgisayarli-goru
A set of strategies aimed at maintaining detection and tracking when the object becomes partially or fully invisible.
🗃️Offline Feature Storeveri-muhendisligi-ve-ai-altyapisi
A historical and large-scale feature storage layer used for model training, backtesting, and batch feature generation.
🕳️One-Class Classificationveri-bilimi-ve-veri-yonetimi
A modeling approach that learns the normal pattern and treats deviations as anomalous when the minority class is extremely rare.
🛡️One-Class SVMmakine-ogrenmesi
A method that learns the normal class and treats observations outside that boundary as anomalies.
⚡One-Stage Detectorbilgisayarli-goru
A family of models that performs fast detection by combining proposal generation and classification in a single forward pass.
⚡Online Diarizationses-konusma-audio-ai
A low-latency diarization approach that performs speaker separation during streaming before the audio is complete.
⚡Online Feature Storeveri-muhendisligi-ve-ai-altyapisi
A feature store layer optimized for low-latency feature serving at live prediction time.
🌊Online Learningyapay-zeka-temelleri
A learning approach in which the model is updated incrementally with new examples arriving over time rather than all at once.
🕸️Open Information Extractiondogal-dil-isleme
An approach that extracts subject-relation-object structures from text without relying on a predefined relation schema.
🗃️Open Table Formatveri-muhendisligi-ve-ai-altyapisi
An open-standard table structure that supports versioning, transactions, and metadata management for large-scale data lake tables.
🚪Open-Set Recognitionbilgisayarli-goru
An approach that enables a model to flag unseen classes as unknown instead of assigning them an overconfident incorrect label.
🌍Open-Vocabulary Detectionbilgisayarli-goru
A detection approach that can perceive a broader object world using natural language labels instead of fixed class lists.
🌍Open-World Object Detectionbilgisayarli-goru
An approach that aims for a model not only to detect known objects but also to handle unknown ones as a separate category.
📡Operational Metadataveri-muhendisligi-ve-ai-altyapisi
The metadata layer containing operational information such as run status, refresh timing, error history, and processing performance.
📄Optical Character Recognitionbilgisayarli-goru
A core Document AI task that converts text within images or documents into machine-processable text.
📉Optimizationyapay-zeka-temelleri
The process of systematically improving model parameters according to an objective function in order to increase performance.
📶Ordinal Classificationmakine-ogrenmesi
A classification approach that leverages the natural ordering of classes in problems where labels have an intrinsic rank.
📦Oriented Object Detectionbilgisayarli-goru
A task focused on detecting rotated or tilted objects with angled boxes instead of axis-aligned boxes.
🧹Orphaned Asset Detectionveri-muhendisligi-ve-ai-altyapisi
A lineage-based control process for identifying data assets that no longer have meaningful upstream or downstream connections.
📐Orthogonalitymatematik-istatistik-optimizasyon
A concept describing two vectors being perpendicular and carrying no linear interaction.
📏Orthonormal Basismatematik-istatistik-optimizasyon
A basis made of vectors that are mutually orthogonal and unit length, simplifying computation and interpretation.
🚨Outlierveri-bilimi-ve-veri-yonetimi
An observation or value that deviates noticeably from the general pattern of the dataset.
⚠️Overfittingyapay-zeka-temelleri
A situation where a model learns the training data too closely and performs poorly on new data.
🔀Overlapped Speech Detectionses-konusma-audio-ai
A task focused on identifying time intervals in which multiple speakers talk simultaneously.
📦Overparameterizationderin-ogrenme
The condition in which a model has a parameter capacity far larger than the amount of available data.
⬆️Oversamplingveri-bilimi-ve-veri-yonetimi
An approach that increases the number of minority-class examples to make them more visible in the dataset.
🌫️Oversmoothing in GNNderin-ogrenme
A problem in which node representations become too similar after excessive message passing, reducing discriminative power.

P

🛡️PII Lineage Trackingveri-muhendisligi-ve-ai-altyapisi
A specialized lineage approach focused on tracking where personal data comes from and where it flows across the data platform.
🗂️Paged Attentionuretken-yapay-zeka-ve-llm
An attention-management technique that handles KV cache memory more efficiently and improves resource use under multi-request serving.
🌐Panoptic Segmentationbilgisayarli-goru
A unified segmentation task that models both scene classes and separate object instances under a single framework.
🪶Parameter Efficient Fine-Tuninguretken-yapay-zeka-ve-llm
A fine-tuning approach that adapts a model using a limited number of parameters instead of updating the full model.
🔁Parameter Sharingderin-ogrenme
An efficient learning principle in which the same weights are reused across multiple positions or structures.
⚙️Parameters and Hyperparametersyapay-zeka-temelleri
The core difference between internal values learned from data and external settings that shape the training process.
🪞Paraphrase Detectiondogal-dil-isleme
The task of determining whether two expressions carry the same or very similar meaning despite surface differences.
⛏️Paraphrase Miningdogal-dil-isleme
The process of automatically discovering sentence pairs with the same or very similar meaning within large text collections.
➗Partial Derivativematematik-istatistik-optimizasyon
A derivative that measures the change of a multivariable function with respect to only one variable.
🧪Partial Least Squares Regressionmakine-ogrenmesi
A regression method that builds target-aware latent components, especially in highly correlated and high-dimensional feature spaces.
🌿Partition Pruningveri-muhendisligi-ve-ai-altyapisi
An optimization technique that reduces cost by processing only relevant partitions in batch jobs and queries.
🧱Partitioningveri-muhendisligi-ve-ai-altyapisi
A technique for improving read, write, and processing efficiency by splitting large datasets into logical partitions.
👀Passive Data Collectionveri-bilimi-ve-veri-yonetimi
An approach in which data is collected through behavior, sensor output, and system traces rather than direct user input.
👁️Perceptionyapay-zeka-temelleri
The core capability of transforming raw inputs into meaningful structures so the system can interpret its environment.
🔹Perceptronderin-ogrenme
The most basic artificial neuron model that learns a linear decision boundary through weighted inputs.
🔀Permutation Testmatematik-istatistik-optimizasyon
A resampling-based test that evaluates whether an observed difference could be due to chance with weaker reliance on distributional assumptions.
❓Perplexitymatematik-istatistik-optimizasyon
A measure, especially common in language models, that summarizes how surprised a probability model is by the data.
🎯Personalized Speech Enhancementses-konusma-audio-ai
An approach focused on extracting a specific target speaker’s voice more effectively from background noise and other speakers.
🌊Phase-Aware Audio Processingses-konusma-audio-ai
An approach that aims for more natural and accurate audio restoration by considering phase information in addition to magnitude.
🔤Phoneme-Aware Keyword Spottingses-konusma-audio-ai
An approach that models keyword spotting not only at the word level but also through phonetic structure.
📡Pipeline Observabilityveri-muhendisligi-ve-ai-altyapisi
An approach that continuously monitors the health, latency, volume, and failure behavior of data pipelines.
⏱️Pipeline SLAveri-muhendisligi-ve-ai-altyapisi
A service standard that defines the expected delivery time, success rate, and availability level of a data pipeline.
🎵Pitch Trackingses-konusma-audio-ai
A core acoustic analysis task that tracks the fundamental frequency of an audio signal over time.
🕰️Point-in-Time Joinveri-muhendisligi-ve-ai-altyapisi
An approach for generating training data using only the historical features that would actually have been available at prediction time.
📡Poisson Distributionmatematik-istatistik-optimizasyon
A discrete distribution used to model the number of events occurring within a fixed interval of time or space.
🔢Poisson Regressionmakine-ogrenmesi
A regression method that models count data by estimating the expected number of events through a log-link function.
🧭Policyyapay-zeka-temelleri
A decision rule or behavioral strategy that defines which action an agent should choose in a given state.
💻Policy as Codeveri-bilimi-ve-veri-yonetimi
An approach in which data access, usage, and security policies are defined and enforced through code instead of manual processes.
📐Polynomial Regressionmakine-ogrenmesi
A method that preserves linear model structure while modeling curved relationships through polynomial terms of input variables.
📦Pooling Layerderin-ogrenme
A layer that summarizes feature maps, reduces dimensionality, and provides robustness to local variations.
👥Population and Samplematematik-istatistik-optimizasyon
The core statistical distinction between the full target group and the subset selected from it for analysis.
📍Positional Encodingderin-ogrenme
A method that injects order information into Transformer models so sequence positions become visible.
⬇️Post-Norm Transformerderin-ogrenme
The classical Transformer variant that applies normalization after the attention or FFN block.
📉Post-Training Quantizationuretken-yapay-zeka-ve-llm
A quantization approach that reduces a pretrained model to lower-bit precision to gain memory and speed benefits.
📉Posterior Collapsederin-ogrenme
A VAE training issue in which the decoder ignores the latent variable, weakening representation learning.
🧭Posterior Probabilitymatematik-istatistik-optimizasyon
A Bayesian probability concept representing updated belief after observing new data.
⬆️Pre-Norm Transformerderin-ogrenme
A Transformer design variant that places normalization before the main attention or FFN block.
🎯Precision-Recall AUCmatematik-istatistik-optimizasyon
An evaluation metric that summarizes how well a model retrieves useful positives, especially in imbalanced settings.
⚖️Preference Optimizationdogal-dil-isleme
An alignment approach that makes model output more useful by optimizing against human or system preference signals.
🏷️Prefix Tuninguretken-yapay-zeka-ve-llm
A PEFT technique that steers the model’s internal attention behavior through small learnable prefix representations.
🛤️Preprocessing Pipelineveri-bilimi-ve-veri-yonetimi
A sequenced, reproducible, and automation-friendly workflow of data transformation steps.
🏗️Pretraininguretken-yapay-zeka-ve-llm
The initial training stage in which a model learns broad patterns from large-scale general data.
🗃️Pretraining Corpusdogal-dil-isleme
The large text data pool used by a language model to acquire general linguistic and world knowledge.
📉Principal Component Analysismakine-ogrenmesi
The most widely used linear dimensionality reduction method that preserves most of the variance in the data.
💰Privacy Budgetveri-bilimi-ve-veri-yonetimi
A concept that quantitatively governs how much privacy loss is allowed in differential privacy applications.
🔐Privacy-Preserving Synthetic Dataveri-bilimi-ve-veri-yonetimi
A synthetic data generation approach designed to create analytical value without exposing real individuals.
🎲Probabilitymatematik-istatistik-optimizasyon
A fundamental mathematical concept that quantifies the likelihood of an event occurring.
💻Programmatic Labelingveri-bilimi-ve-veri-yonetimi
An approach in which labels are generated automatically through code, rules, or functions rather than manual entry.
📄Prompt Templateuretken-yapay-zeka-ve-llm
A parameterized prompt pattern that provides reusable and consistent structure across repeated tasks.
🪄Prompt-Based Classificationdogal-dil-isleme
An approach that solves classification problems directly through natural language instructions and label descriptions.
🪄Promptable Segmentationbilgisayarli-goru
A flexible visual separation approach that performs segmentation guided by prompts such as points, boxes, or text.
📘Pronunciation Lexiconses-konusma-audio-ai
A resource that maps written words to phonetic forms and builds an acoustic-linguistic bridge in hybrid speech recognition systems.
🗓️Prophetmakine-ogrenmesi
A modern time series tool developed to flexibly model trend, seasonality, and holiday effects.
🎼Prosodic Emotion Cuesses-konusma-audio-ai
An approach that uses suprasegmental speech features such as pitch, rhythm, energy, and pauses for emotional interpretation.
🎼Prosody Modelingses-konusma-audio-ai
An approach that models emphasis, rhythm, intonation, and pause structure to produce more natural speech synthesis.
🪜Proximal Gradientmatematik-istatistik-optimizasyon
An optimization method used for problems that combine smooth and non-smooth objective components.
🪪Pseudonymizationveri-bilimi-ve-veri-yonetimi
An approach that replaces direct identifiers with substitute representations that can be re-linked only through controlled additional information.
⬇️Pushdown Transformationveri-muhendisligi-ve-ai-altyapisi
An approach in which transformations are executed inside the engine or platform where the data already resides rather than in a separate layer.
📉p-Valuematematik-istatistik-optimizasyon
The probability of observing a result at least as extreme as the one obtained, assuming the null hypothesis is true.

Q

💾QLoRAuretken-yapay-zeka-ve-llm
An approach that performs LoRA adaptation on a quantized base model to enable fine-tuning at lower hardware cost.
📊Quantile Regressionmakine-ogrenmesi
A regression approach that models specific quantiles of the target variable rather than only its mean.
📈Quantile Transformationveri-bilimi-ve-veri-yonetimi
A transformation that reshapes data through rank-based mapping to make it more regular or closer to a target distribution.
⚙️Quantization Aware Traininguretken-yapay-zeka-ve-llm
An approach that trains the model under low-precision conditions to preserve quality after quantization.
⚡Query Accelerationveri-muhendisligi-ve-ai-altyapisi
An optimization approach that enables data warehouse queries to run with lower latency and higher efficiency.
🔎Query Expansiondogal-dil-isleme
An approach that broadens retrieval coverage by enriching the user query with synonyms, related terms, or rewrites.
🎯Query-Focused Summarizationdogal-dil-isleme
A summarization approach that focuses on a specific user query or information need rather than producing a general summary.
🔑Query-Key-Value Representationderin-ogrenme
A representation scheme in attention mechanisms that structures information access through the query, key, and value separation.
🔎Query-by-Example Keyword Spottingses-konusma-audio-ai
An approach that searches for similar words or phrases in audio streams by using an example audio query instead of text.

R

⚡RNN-Transducerses-konusma-audio-ai
An end-to-end ASR architecture that provides a strong balance between low latency and accuracy in streaming speech recognition.
📈ROC-AUCmatematik-istatistik-optimizasyon
A widely used comparison metric that summarizes a classifier’s ability to separate positives and negatives across thresholds.
🌲Random Forestmakine-ogrenmesi
An ensemble learning method that combines the outputs of multiple decision trees to make more robust predictions.
🎲Random Projectionmakine-ogrenmesi
A computationally efficient method that projects high-dimensional data into a lower-dimensional space while approximately preserving distances.
🎲Random Searchmakine-ogrenmesi
An optimization approach that searches for effective combinations by randomly sampling the hyperparameter space.
🎯Random Variablematematik-istatistik-optimizasyon
A mathematical variable that maps the possible outcomes of a random experiment to numerical values.
📚Rankmatematik-istatistik-optimizasyon
A structural measure that expresses the number of linearly independent rows or columns in a matrix.
🏁Ranking-Based Recommendationmakine-ogrenmesi
An approach that optimizes recommendation quality by focusing on presenting items in the right order.
🚨Rare Event Modelingveri-bilimi-ve-veri-yonetimi
An approach that requires specialized strategies to model low-frequency but high-impact events.
🪵Raw Zoneveri-muhendisligi-ve-ai-altyapisi
The data lake layer where source data is first accepted with minimal alteration.
🪪Re-Identificationbilgisayarli-goru
A task that enables the re-matching of an object or person across cameras or separated time intervals.
🕵️Re-identification Riskveri-bilimi-ve-veri-yonetimi
A privacy risk describing the possibility of identifying individuals again from anonymized or restricted datasets.
⚡ReLU Activationderin-ogrenme
The most common modern activation function, which zeros negative inputs and leaves positive inputs linear.
⚡Reactive Machineyapay-zeka-temelleri
A basic type of AI system that responds only to current input without persistently using past experience.
📖Reading Comprehensiondogal-dil-isleme
A family of tasks that measures the ability to read a text and answer meaningful questions based on its content.
📚Reading Order Detectionbilgisayarli-goru
A task that determines the order in which document content should be read to reconstruct the correct text flow.
⚡Real-Time Feature Computationveri-muhendisligi-ve-ai-altyapisi
An approach in which feature values are computed close to prediction time instead of being fully precomputed.
🧠Reasoningyapay-zeka-temelleri
The process of deriving new conclusions from available knowledge, rules, or observations and grounding decisions.
👁️Receptive Fieldderin-ogrenme
A concept describing which region of the input contributes information to a neuron or feature activation.
🧾Reconciliation Controlveri-bilimi-ve-veri-yonetimi
The process of verifying alignment of records, totals, and business logic across different data systems or layers.
🔗Record Linkageveri-bilimi-ve-veri-yonetimi
The process of linking records belonging to the same person, organization, or event across multiple data sources.
🔄Recurrent Neural Networkderin-ogrenme
A foundational neural network family that models sequential data by carrying information from past time steps.
🗃️Reference Data Managementveri-bilimi-ve-veri-yonetimi
The centralized and consistent management of controlled data sets such as code lists, classes, and shared dictionaries.
📍Referring Expression Comprehensionbilgisayarli-goru
A task that matches a natural language description to the correct region in an image.
🛠️Regularizationyapay-zeka-temelleri
A set of techniques used to reduce overfitting and improve a model’s ability to generalize.
🎮Reinforcement Learningyapay-zeka-temelleri
A paradigm in which an agent learns a long-term behavior policy through rewards and penalties by interacting with its environment.
🎛️Reinforcement Learning from Human Feedbackuretken-yapay-zeka-ve-llm
An alignment approach that uses reward signals to make model outputs more consistent with human preferences.
🕸️Relation Extractiondogal-dil-isleme
The task of identifying meaningful relation types between entities mentioned in text.
🎲Reparameterization Trickderin-ogrenme
A core VAE technique that makes latent-variable models with stochastic sampling differentiable.
🧬Representation Learningyapay-zeka-temelleri
An approach in which informative, discriminative, and task-relevant internal representations are learned automatically from raw data.
🏁Rerankingdogal-dil-isleme
A second-stage quality-improvement method that reranks candidates from the first retrieval stage using a stronger model.
♻️Rerun Strategyveri-muhendisligi-ve-ai-altyapisi
An approach that defines how failed or incomplete data jobs should be rerun and under what safety rules.
➕Residual Blockderin-ogrenme
A building block that eases the training of deep CNNs by carrying information directly through identity connections.
🗄️Retention Policyveri-bilimi-ve-veri-yonetimi
A governance policy that defines how long data is retained, and when it should be archived or deleted.
📚Retrieval-Augmented Generationdogal-dil-isleme
An architectural approach that supports model generation with external knowledge sources to produce more current and grounded answers.
↩️Reverse ETLveri-muhendisligi-ve-ai-altyapisi
An integration approach that moves curated data from analytics platforms back into operational systems.
🏆Reward Functionyapay-zeka-temelleri
A feedback mechanism that numerically defines which outcomes the system should consider more valuable.
🏆Reward Modeluretken-yapay-zeka-ve-llm
An auxiliary model that estimates how preferable generated outputs are and provides signals for alignment.
🧮Ridge Regressionmakine-ogrenmesi
A regression method with L2 regularization that reduces overfitting by penalizing coefficient magnitude.
🛡️Robust Covariance Anomaly Detectionmakine-ogrenmesi
A statistical approach that performs anomaly detection through covariance estimation that is more robust to outliers.
🪟Rolling Window Featuresveri-bilimi-ve-veri-yonetimi
A feature structure that summarizes past observations within a defined window to generate time-dependent signals.
🌀Rotary Positional Embeddingderin-ogrenme
A modern positional representation method that encodes order information through rotations in vector space.
📜Rule-Based Data Cleansingveri-bilimi-ve-veri-yonetimi
A cleansing approach that improves data quality through explicit business rules and validation conditions.
📜Rule-Based Systemyapay-zeka-temelleri
A classical system architecture whose behavior is determined by predefined if-then rules.

S

🔁SARIMAmakine-ogrenmesi
An extended ARIMA model that also includes seasonal components.
📊SELU Activationderin-ogrenme
An activation function designed to support self-normalizing network behavior.
🧠SIFT Descriptorbilgisayarli-goru
A classical but effective descriptor method that produces local visual features robust to scale and rotation.
🧬SMOTEveri-bilimi-ve-veri-yonetimi
A widely used balancing technique that generates new synthetic examples for the minority class from existing ones.
⚙️SORT Trackerbilgisayarli-goru
A lightweight system that performs fast multi-object tracking by combining Kalman filtering with Hungarian assignment.
🐎Saddle Pointmatematik-istatistik-optimizasyon
A type of point that behaves like a minimum in some directions and a maximum in others, often complicating optimization.
🔄Sample Rate Conversionses-konusma-audio-ai
A process that adapts an audio signal to different sampling rates for model and system compatibility.
🎲Samplinguretken-yapay-zeka-ve-llm
The process of making probabilistic choices from a learned distribution while generating new output.
🧭Sampling Frameveri-bilimi-ve-veri-yonetimi
The source list or coverage structure that defines which units can enter the sampling process.
🎯Scaled Dot-Product Attentionderin-ogrenme
The fundamental Transformer operation that computes attention weights by scaling similarity between query and key vectors.
📈Scaling Lawsuretken-yapay-zeka-ve-llm
A set of empirical regularities describing how performance changes as model size, data, and compute increase.
🗓️Scheduled Samplingderin-ogrenme
A method that gradually reduces teacher forcing to bring training conditions closer to inference conditions.
🧱Schema Driftveri-bilimi-ve-veri-yonetimi
The risk that changes in data structure over time will break existing processing and analytics workflows.
📖Schema-on-Readveri-muhendisligi-ve-ai-altyapisi
A flexible data-processing approach in which schema is applied when data is read rather than when it is written.
⚖️Score Normalizationses-konusma-audio-ai
A process that makes similarity scores in speaker verification systems more stable and comparable.
🗺️Search Spaceyapay-zeka-temelleri
The conceptual space that contains all possible states, solution paths, and action combinations of a problem.
🪞Self-Attentionderin-ogrenme
An attention mechanism in which each element in a sequence directly models its relationship with all others.
💡Self-Informationmatematik-istatistik-optimizasyon
An information-theoretic concept that measures how much information is gained when a single event occurs.
🧱Self-Supervised Learningyapay-zeka-temelleri
An approach that enables strong representation learning by generating supervision signals from the internal structure of the data itself.
🧬Self-Supervised Visual Featuresbilgisayarli-goru
Visual representations learned without labels that can be reused across many downstream vision tasks.
⚡Semantic Cachingdogal-dil-isleme
A system approach that reduces latency and cost by reusing prior answers for semantically identical or similar queries.
🧠Semantic Layerveri-muhendisligi-ve-ai-altyapisi
A layer that abstracts business metrics, definitions, and query logic consistently above technical data structures.
🧠Semantic Lineageveri-muhendisligi-ve-ai-altyapisi
A lineage approach that shows how data assets are derived and connected not only technically, but also at the business-meaning level.
🧩Semantic Segmentationbilgisayarli-goru
A task that assigns a class label to every pixel in an image for pixel-level scene understanding.
🤝Semantic Textual Similaritydogal-dil-isleme
A task that measures how semantically close two texts are regardless of surface-level overlap.
🪄Semi-Supervised Learningyapay-zeka-temelleri
An approach that improves learning performance by combining a small amount of labeled data with a large amount of unlabeled data.
🧪Semi-Supervised Segmentationbilgisayarli-goru
An approach that improves segmentation quality by using a small set of labeled examples together with many unlabeled images.
📍Sentence Boundary Detectiondogal-dil-isleme
The task of reliably identifying sentence starts and boundaries in text.
🧾Sentence Embeddingsdogal-dil-isleme
An embedding approach focused on producing semantic representations at the sentence or short-text level.
🧱SentencePiecedogal-dil-isleme
A tokenization framework that can learn subword vocabularies from raw text without relying on whitespace segmentation.
😊Sentiment Analysisdogal-dil-isleme
An NLP task focused on determining the positive, negative, or neutral emotional orientation of a text.
🔀Sequence-to-Sequence Learningderin-ogrenme
A general modeling approach focused on converting one input sequence into another output sequence.
🕒Session-Based Recommendationmakine-ogrenmesi
A recommendation approach based on the behavior flow within the current session rather than long-term user history.
🪶Sharpness-Aware Minimizationderin-ogrenme
An optimization approach that seeks not only low loss but also flatter and more generalizable solution regions.
📐Short-Time Fourier Transformses-konusma-audio-ai
A core transform that enables windowed analysis of audio frequency content over time.
🎬Shot Boundary Detectionbilgisayarli-goru
A task that identifies scene or camera-shot transitions in video to enable structural video analysis.
📉Sigmoid Activationderin-ogrenme
A classical activation function that squashes input values into the range between 0 and 1.
🧲Similarityyapay-zeka-temelleri
A core concept used to measure how close, related, or semantically similar two examples are.
📐Similarity Metricveri-muhendisligi-ve-ai-altyapisi
The core retrieval criterion that defines how proximity between vectors is computed.
🕹️Simulation Dataveri-bilimi-ve-veri-yonetimi
Data generated by imitating the behavior of real systems through mathematical or rule-based models.
🎯Single Object Trackingbilgisayarli-goru
A task that continuously updates the location of a selected object over time in video.
🏷️Single-Label Image Classificationbilgisayarli-goru
A fundamental vision task that assigns an image to exactly one of a set of predefined classes.
🪓Singular Value Decomposition (SVD)matematik-istatistik-optimizasyon
A powerful decomposition method that breaks a matrix into more fundamental components for structure analysis, compression, and dimensionality reduction.
📉Skewnessmatematik-istatistik-optimizasyon
A measure showing whether a distribution is symmetric and in which direction its tail extends.
⤴️Skip Connectionderin-ogrenme
An architectural connection that allows information to bypass certain layers and improves training stability.
🧾Slot Fillingdogal-dil-isleme
An information extraction approach focused on automatically filling predefined information fields from text.
🕰️Slowly Changing Dimensionveri-muhendisligi-ve-ai-altyapisi
A warehouse approach that defines how changing dimension attributes should be preserved historically over time.
📟Small-Footprint Keyword Spottingses-konusma-audio-ai
An approach focused on designing lightweight keyword spotting models for devices with limited memory and compute.
🎛️Softmax Activationderin-ogrenme
An output activation that expresses multiclass outputs as a normalized probability distribution.
📡Sound Event Localization and Detectionses-konusma-audio-ai
An advanced environmental audio task that determines not only the presence of a sound event but also its timing and sometimes direction.
🧩Source Separationses-konusma-audio-ai
A task that aims to separate a mixed audio signal into components such as speech, music, or individual speakers.
🪞Source System Replicationveri-muhendisligi-ve-ai-altyapisi
An approach in which data from a source system is replicated into another environment for analytical or operational use.
🧾Sparse Attentionderin-ogrenme
An attention approach that reduces cost by allowing each element to attend only to selected regions rather than the full sequence.
🧬Sparse Autoencoderderin-ogrenme
A type of autoencoder that encourages only a small number of latent neurons to activate, leading to more selective features.
🗂️Sparse Neural Embeddingsdogal-dil-isleme
A representation approach that uses neural models to produce semantic signals while preserving sparse-retrieval-style interpretability.
🗂️Sparse Retrievaldogal-dil-isleme
A classical yet still powerful retrieval approach based on term- or word-level matching.
🎞️Spatio-Temporal Convolutionbilgisayarli-goru
A convolutional approach that jointly models spatial patterns and temporal change within video.
🧩Speaker Clusteringses-konusma-audio-ai
A diarization subtask that groups similar speech segments so they correspond to the same speaker.
👥Speaker Diarizationses-konusma-audio-ai
The task of determining who spoke when over the timeline of an audio recording.
🧠Speaker Embeddingsses-konusma-audio-ai
Dense vector representations that capture speaker identity in a discriminative form.
🪪Speaker Identificationses-konusma-audio-ai
A task that determines which enrolled speaker in a known set produced a given voice sample.
✅Speaker Verificationses-konusma-audio-ai
A binary decision problem that verifies whether a voice sample belongs to the claimed speaker.
🧠Speaker-Independent Emotion Recognitionses-konusma-audio-ai
An approach that aims for emotion models to learn general affective cues without overfitting to speaker-specific voice traits.
🌐Spectral Clusteringmakine-ogrenmesi
A clustering method that aims to discover complex cluster structures using similarity graphs and eigen decomposition.
⚡Speculative Decodinguretken-yapay-zeka-ve-llm
A decoding approach that speeds up generation by validating proposals from a smaller fast model with a larger model.
🎭Speech Emotion Recognitionses-konusma-audio-ai
A task that attempts to infer emotional state by extracting affective acoustic cues from speech.
🧼Speech Enhancementses-konusma-audio-ai
A processing task that aims to make speech more intelligible from noisy or degraded audio.
✍️Spelling Correctiondogal-dil-isleme
A preprocessing technique that converts misspelled text into more accurate forms to improve downstream NLP quality.
📡Squeeze-and-Excitationderin-ogrenme
A CNN module that reweights feature channels using global context.
🧱Stackingmakine-ogrenmesi
An ensemble technique that combines the outputs of multiple base models through a higher-level meta-model.
🪜Staging Areaveri-muhendisligi-ve-ai-altyapisi
An intermediate preparation layer where source data is temporarily held before final transformation.
🧭Stance Detectiondogal-dil-isleme
A task focused on identifying a text’s stance toward a given claim, topic, or target.
⚖️Standardizationveri-bilimi-ve-veri-yonetimi
The process of transforming a variable so that it has mean zero and standard deviation one.
⭐Star Schemaveri-muhendisligi-ve-ai-altyapisi
A classic analytical warehouse design with a central fact table surrounded by dimension tables.
🧾Stateyapay-zeka-temelleri
A meaningful description of a system or environment at a given moment for decision-making purposes.
🗄️State Storeveri-muhendisligi-ve-ai-altyapisi
A persistent or semi-persistent data structure that stores historical context and intermediate computation state during stream processing.
🔋Statistical Powermatematik-istatistik-optimizasyon
The probability that a statistical test will detect an effect when that effect truly exists.
🌱Stemmingdogal-dil-isleme
An approach that reduces a word to a shorter root-like form by crudely stripping suffixes.
🎲Stochastic Depthderin-ogrenme
A method that provides stronger regularization in very deep networks by randomly skipping some layers during training.
🎇Stochastic Generationuretken-yapay-zeka-ve-llm
A generation mode that introduces probabilistic diversity instead of producing the exact same output every time.
🏃Stochastic Gradient Descentmatematik-istatistik-optimizasyon
An optimization approach that updates parameters using single examples or small subsets instead of the full dataset at each step.
🧮Stochastic Weight Averagingderin-ogrenme
A method that averages parameter states from different stages of training in order to obtain more robust generalization.
🚫Stopword Filteringdogal-dil-isleme
A classical preprocessing technique based on removing frequent words that are assumed to have low semantic contribution.
🪢Stream Joinveri-muhendisligi-ve-ai-altyapisi
The operation of joining multiple continuous data streams by key and time logic to create meaningful event context.
🐢Stream Lagveri-muhendisligi-ve-ai-altyapisi
A core stream-health metric that expresses the delay gap between produced events and consumed events.
⚡Stream Processingveri-muhendisligi-ve-ai-altyapisi
A processing approach based on handling continuously arriving data events with low latency.
🪟Stream Windowingveri-muhendisligi-ve-ai-altyapisi
An approach that groups continuous data streams into defined time or event intervals for computation.
🌊Streaming Data Collectionveri-bilimi-ve-veri-yonetimi
An approach for ingesting continuously generated data in real time or near real time.
⏹️Streaming Endpoint Detectionses-konusma-audio-ai
A mechanism that determines when speech has truly ended in order to provide correct response timing in streaming ASR systems.
⚡Streaming TTSses-konusma-audio-ai
A real-time speech synthesis approach that begins generating audio with low latency without waiting for the full text.
⚠️Stress Detection from Speechses-konusma-audio-ai
A task that attempts to extract stress or cognitive-load signals from acoustic variations in speech.
👣Stridederin-ogrenme
A CNN hyperparameter that determines how many steps a filter moves across the input and affects output resolution.
🧾Structured Output Promptingdogal-dil-isleme
A technique that asks the model to produce schema-aligned outputs such as JSON or tables instead of free text.
🧩Subword Tokenizationdogal-dil-isleme
An approach that splits rare words into smaller meaningful pieces to balance vocabulary size and coverage.
✂️Successive Halvingmakine-ogrenmesi
An optimization approach that evaluates model candidates in stages, eliminates weak ones, and allocates resources to the strongest candidates.
🧾Sufficiencymatematik-istatistik-optimizasyon
The property of a statistic containing all relevant information in the data about a parameter.
🧭Summary Faithfulnessdogal-dil-isleme
A quality dimension describing how faithfully a generated summary remains grounded in the source text.
🎯Supervised Fine-Tuningdogal-dil-isleme
The process of steering a pretrained model toward more specific behavior using labeled task data.
🏷️Supervised Learningyapay-zeka-temelleri
A core learning paradigm in which the relationship between inputs and target outputs is learned from labeled examples.
📐Support Vector Machinemakine-ogrenmesi
A powerful classification method that aims to separate classes by maximizing the margin between them.
🌊Swish Activationderin-ogrenme
A modern activation function that multiplies the input by a sigmoid to create a smooth nonlinear transformation.
🔣Symbolic AIyapay-zeka-temelleri
A classical AI approach that performs inference by representing knowledge with rules, symbols, and logical expressions.
🧬Synthetic Dataveri-bilimi-ve-veri-yonetimi
Artificially generated data designed to imitate real data distributions for analysis or modeling purposes.
🧪Synthetic Data Fidelityveri-bilimi-ve-veri-yonetimi
A property indicating how well synthetic data preserves the statistical, structural, and use-case-relevant characteristics of real data.
🧯Synthetic Data Leakageveri-bilimi-ve-veri-yonetimi
A risk in which synthetic data leaks membership or privacy-sensitive information because it preserves too much trace of the real data.
🧭System Prompturetken-yapay-zeka-ve-llm
A high-level instruction layer that defines the model’s overall behavior, role, and priorities.

T

📊Table Structure Recognitionbilgisayarli-goru
A task that extracts row, column, and cell relationships in document tables so the data becomes machine-usable.
⚖️Tanh Activationderin-ogrenme
A zero-centered activation function that maps inputs into the range from -1 to 1.
🎯Target Encodingveri-bilimi-ve-veri-yonetimi
An advanced feature engineering technique that converts categorical levels into numerical representations using target-related summary statistics.
👨‍🏫Teacher Forcingderin-ogrenme
A training strategy in sequence generation where the model is fed the true previous output instead of its own prediction.
🧾Technical Metadataveri-muhendisligi-ve-ai-altyapisi
The technical metadata layer that describes schema, data types, source structures, and storage characteristics of data assets.
🌡️Temperature Samplinguretken-yapay-zeka-ve-llm
A parameter that adjusts output distribution sharpness to produce more controlled or more creative generation.
📄Template-Based Extractiondogal-dil-isleme
A controlled extraction approach focused on obtaining structured information from predefined document or expression patterns.
⏱️Temporal Action Localizationbilgisayarli-goru
A task that identifies not only the action type in a video but also the time interval in which it occurs.
✂️Temporal Action Segmentationbilgisayarli-goru
A task that segments long video streams into meaningful action units and assigns an action label to each temporal interval.
📅Temporal Cross-Validationmakine-ogrenmesi
An approach that performs chronological validation in time series problems to prevent future information from leaking into the past.
🧊Tensormatematik-istatistik-optimizasyon
A multidimensional numerical structure that generalizes scalars, vectors, and matrices.
🖥️Tensor Parallelismuretken-yapay-zeka-ve-llm
A technique that scales inference and training by splitting large model computations across devices within layers.
📚Terminology-Constrained Translationdogal-dil-isleme
A controlled machine translation approach that preserves required translation equivalents for specific terms.
📊Test Statisticmatematik-istatistik-optimizasyon
A computed measure that summarizes how unusual the data is in the context of a hypothesis test.
🏷️Text Classificationdogal-dil-isleme
The task of assigning a text to one or more predefined categories, intents, or labels.
🧽Text Deduplicationdogal-dil-isleme
A process that removes identical or near-duplicate text samples from a dataset to improve training and evaluation quality.
🔍Text Detection in Documentsbilgisayarli-goru
A document vision task that locates text regions before character recognition is performed.
🧹Text Normalizationdogal-dil-isleme
The process of standardizing raw text at the spelling, formatting, and character levels to make it more consistent and processable.
🔐Text-Dependent Speaker Verificationses-konusma-audio-ai
A more controlled speaker verification approach in which the speaker says a fixed phrase or passphrase.
🖼️Text-to-Image Generationuretken-yapay-zeka-ve-llm
A generative modeling approach that synthesizes new images from natural language prompts.
🎚️Threshold Movingveri-bilimi-ve-veri-yonetimi
An approach that adjusts the classification threshold according to business goals and error costs in imbalanced settings.
🕒Time-Based Splitveri-bilimi-ve-veri-yonetimi
An approach in which training and evaluation sets are split chronologically for time-dependent data.
⏰Timelinessveri-bilimi-ve-veri-yonetimi
The property of data being sufficiently current, timely, and available when needed.
🔗Token Alignmentdogal-dil-isleme
The problem of preserving the mapping between subword tokens and original word or span structures.
✂️Tokenizationdogal-dil-isleme
The core language processing step that splits text into units that a model can process.
🔤Tokenizeruretken-yapay-zeka-ve-llm
A core intermediary layer that converts text into tokens the model can process.
🛠️Tool-Augmented Generationuretken-yapay-zeka-ve-llm
An approach in which the model uses tools such as computation, search, or external system calls to produce more accurate results.
🚨Toxicity Detectiondogal-dil-isleme
A safety-focused NLP task aimed at identifying insults, aggression, hate speech, or other harmful language use.
🔗Tracking-by-Detectionbilgisayarli-goru
A common approach that performs object detection on each frame and builds tracks by associating detections over time.
🪟Train / Validation / Test Splitmatematik-istatistik-optimizasyon
A core data splitting approach used to separate model learning, tuning, and final evaluation in an honest way.
⚙️Train-Serve Skewveri-bilimi-ve-veri-yonetimi
A mismatch between the data seen during training and the data encountered in production at serving time.
🔄Transfer Learningyapay-zeka-temelleri
An approach in which knowledge learned from one task is transferred to a related task to reduce training cost and data requirements.
🔁Transfer Learning in Visionbilgisayarli-goru
An approach based on reusing visual models pretrained on large datasets for new tasks.
🔁Transferabilityuretken-yapay-zeka-ve-llm
The ability of a model to transfer what it learned during pretraining into different tasks and domains.
📜Transformation Audit Chainveri-muhendisligi-ve-ai-altyapisi
A trace structure that stores, in auditable form, in what order, under what logic, and under which version data transformations were applied.
🧱Transformation Layerveri-muhendisligi-ve-ai-altyapisi
A rule-driven processing layer that reshapes raw data for analytical or operational use.
🔧Transformer Feed-Forward Networkderin-ogrenme
A Transformer sub-block that operates independently on each token and strengthens representation transformation.
🔼Transposed Convolutionderin-ogrenme
A learnable upsampling layer that maps feature maps to higher spatial resolution.
🌳Tree-Structured Parzen Estimatormakine-ogrenmesi
A Bayesian search method that proposes new hyperparameter candidates by modeling good and bad regions based on previous trials.
🔺Triplet Lossmatematik-istatistik-optimizasyon
A representation learning loss that pulls similar examples closer together and pushes dissimilar ones apart.
✂️Truncated BPTTderin-ogrenme
A method that makes training more tractable on long sequences by applying backpropagation over a limited window.
📚Truncated SVDmakine-ogrenmesi
A truncated singular value decomposition method used for dimensionality reduction, especially in sparse matrices.
🧪Turing Testyapay-zeka-temelleri
One of the most symbolic thought experiments in AI history, asking whether a machine can communicate in a human-like way.
🎯Two-Stage Detectorbilgisayarli-goru
An architectural approach that first proposes candidate regions and then classifies them for more precise object detection.
⚠️Type I and Type II Errormatematik-istatistik-optimizasyon
The two fundamental error types in hypothesis testing: false alarm and failing to detect a real effect.
📊t-Closenessveri-bilimi-ve-veri-yonetimi
A model that requires sensitive-value distributions within anonymized groups to remain close to the overall dataset distribution.
📘t-Distributionmatematik-istatistik-optimizasyon
A continuous distribution used especially to model uncertainty around the mean in small samples.
🌀t-SNEmakine-ogrenmesi
A method focused on preserving local similarity structure when visualizing high-dimensional data in low dimensions.

U

🧬U-Netbilgisayarli-goru
An encoder-decoder segmentation architecture especially effective in biomedical and pixel-level tasks.
🧬UMAPmakine-ogrenmesi
A modern and efficient dimensionality reduction technique that attempts to preserve both local and global data structure.
📏Uncertainty Calibrationuretken-yapay-zeka-ve-llm
A quality approach aimed at making model confidence better aligned with actual correctness.
⬇️Undersamplingveri-bilimi-ve-veri-yonetimi
An approach that reduces the number of majority-class examples to produce a more balanced class distribution.
🔤Unicode Normalizationdogal-dil-isleme
The process of converting visually identical but differently encoded characters into a standard form.
📐Uniform Distributionmatematik-istatistik-optimizasyon
A distribution in which all values within a given interval are equally likely.
🎲Unigram Language Model Tokenizationdogal-dil-isleme
A method that learns a subunit vocabulary probabilistically to make token segmentation more data-aligned.
📘Universal Approximation Theoremderin-ogrenme
A theoretical result stating that a neural network with sufficient capacity can approximate a very broad class of functions.
🧩Unsupervised Learningyapay-zeka-temelleri
A learning approach focused on discovering structure, relationships, and latent patterns in unlabeled data.
👁️Usage Metadataveri-muhendisligi-ve-ai-altyapisi
A type of metadata showing who uses a data asset, how often, and for what purposes.
⚖️Utility Functionyapay-zeka-temelleri
A function that quantitatively expresses how desirable different outcomes or decisions are.

V

✅Validationyapay-zeka-temelleri
An intermediate evaluation stage used to assess how well a model generalizes during training and to improve its settings.
🛡️Validityveri-bilimi-ve-veri-yonetimi
A quality dimension indicating whether a data value conforms to defined formats, ranges, vocabularies, or business rules.
📏Variance and Standard Deviationmatematik-istatistik-optimizasyon
Core measures of variability that quantify how spread out data points are around the mean.
🎨Variational Autoencoderderin-ogrenme
A generative autoencoder architecture that models the latent space probabilistically for both representation and generation.
➡️Vectormatematik-istatistik-optimizasyon
A quantity with direction and magnitude, and one of the most fundamental representations in linear algebra.
🔗Vector Autoregressionmakine-ogrenmesi
A multivariate time series method that jointly models multiple series through their mutually influencing past values.
🚀Vector Cacheveri-muhendisligi-ve-ai-altyapisi
A performance layer that temporarily stores frequently requested embeddings or retrieval results for faster access.
🧲Vector Databaseveri-muhendisligi-ve-ai-altyapisi
A storage and retrieval system optimized for high-dimensional embedding data and similarity search.
⚖️Vector Normalizationveri-muhendisligi-ve-ai-altyapisi
The process of controlling embedding magnitude effects to produce more stable retrieval behavior.
🧊Vector-Quantized Autoencoderderin-ogrenme
A generative autoencoder architecture that uses a discrete codebook instead of a continuous latent space.
✅Verification Loopuretken-yapay-zeka-ve-llm
A workflow pattern that attempts to validate model output through additional checks, source review, or second-stage verification.
🚨Video Anomaly Detectionbilgisayarli-goru
A task focused on detecting deviations from normal behavior patterns in video streams.
📝Video Summarizationbilgisayarli-goru
A task that compresses long video streams into shorter, high-representation summaries with minimal information loss.
🧠Video Transformerbilgisayarli-goru
A modern architectural approach that tokenizes video across time and space and models it with attention mechanisms.
🧠Vision Transformer Featuresbilgisayarli-goru
A modern visual feature structure that splits images into patch tokens and learns representations through global attention.
🧠Vision-Language Modelbilgisayarli-goru
A multimodal model family that combines visual and textual information within a shared representation or generation framework.
🧠Visual Document Understandingbilgisayarli-goru
An approach that jointly interprets text, layout, and visual elements in a document to build higher-level semantic understanding.
❓Visual Question Answeringbilgisayarli-goru
A multimodal task that answers natural language questions about an image based on visual context.
🌊Vocoderses-konusma-audio-ai
A core synthesis component that generates an audible waveform from acoustic representations or spectral features.
📍Voice Activity Detectionses-konusma-audio-ai
A core timing task that determines which parts of an audio signal contain speech.
🛡️Voice Anti-Spoofingses-konusma-audio-ai
A security task that distinguishes genuine user speech from replay attacks, synthesized voices, or converted speech.
🧬Voice Cloningses-konusma-audio-ai
An approach that learns speaker similarity from a short sample and synthesizes new speech resembling the same person.
🗳️Voting Ensemblemakine-ogrenmesi
A simple but effective ensemble method that combines predictions from multiple models through majority vote or averaging.

W

🔔Wake Word Detectionses-konusma-audio-ai
A task that detects a short trigger phrase in continuous audio to activate a device or system.
🗝️Warehouse Partition Keyveri-muhendisligi-ve-ai-altyapisi
The primary partitioning field used to split warehouse tables into logical segments.
💧Watermarkingveri-muhendisligi-ve-ai-altyapisi
A mechanism in stream systems that defines a tolerance boundary for time progression in order to manage late-arriving events.
🧠Wav2Vec 2.0 Pretrainingses-konusma-audio-ai
A self-supervised approach that learns strong speech representations from unlabeled audio and improves ASR and speech tasks.
🪄Weak Supervisionveri-bilimi-ve-veri-yonetimi
An approach that generates approximate labels through rules, heuristics, or weak sources instead of full manual labeling.
🪶Weakly Supervised Segmentationbilgisayarli-goru
An approach that aims to learn segmentation from cheaper labels instead of full pixel masks.
🕸️Web Scrapingveri-bilimi-ve-veri-yonetimi
A method for programmatically collecting structured or semi-structured data from web pages.
⚓Weight Decayderin-ogrenme
A regularization approach that penalizes weight magnitude in order to control model complexity.
🪟Windowing in Audioses-konusma-audio-ai
A fundamental processing step that enables local frequency analysis by splitting the signal into small time segments.
✂️Winsorizationveri-bilimi-ve-veri-yonetimi
An approach that caps extreme values at defined thresholds instead of removing them entirely.
📐Word2Vecdogal-dil-isleme
A historical embedding approach that represents word meaning through dense vectors learned from contextual co-occurrence.
🧠WordPiecedogal-dil-isleme
A widely used tokenization method that optimizes subword units with respect to probabilistic coverage.
🎼Workflow Orchestrationveri-muhendisligi-ve-ai-altyapisi
An approach for centrally managing multiple data processing steps through dependency, sequencing, and scheduling rules.
🚧Workload Isolationveri-muhendisligi-ve-ai-altyapisi
A warehouse approach in which resources are separated to prevent different query and compute workloads from interfering with one another.

X

⚙️XGBoostmakine-ogrenmesi
An advanced gradient boosting method and library known for its speed, performance, and regularization features.
🧠x-vectorses-konusma-audio-ai
A modern speaker recognition approach designed to produce fixed-dimensional embeddings representing speaker identity.

Z

🪄Zero-Shot Image Classificationbilgisayarli-goru
An approach in which a model recognizes new classes without additional training through textual descriptions or shared representation space.
🧬Zero-Shot TTSses-konusma-audio-ai
An advanced TTS approach that can synthesize a new speaker’s voice from short reference samples without additional speaker-specific training.
🪄Zero-Shot Text Classificationdogal-dil-isleme
An approach in which a model classifies texts for new labels without additional training by using natural language label descriptions.