Glossary Library

Technical GlossaryGenerative AI and LLM

Transferability

The ability of a model to transfer what it learned during pretraining into different tasks and domains.

Transferability is one of the central value propositions of the foundation model paradigm. The ability to adapt a single pretrained model to many downstream tasks offers strong benefits in both cost and development speed. It is one of the key criteria for understanding whether a model is truly general-purpose.

You Might Also Like

Explore these concepts to continue your artificial intelligence journey.

Glossary Cover

yapay-zeka-temelleri

Self-Supervised Learning

An approach that enables strong representation learning by generating supervision signals from the internal structure of the data itself.

Glossary Cover

matematik-istatistik-optimizasyon

Train / Validation / Test Split

A core data splitting approach used to separate model learning, tuning, and final evaluation in an honest way.

Glossary Cover

veri-bilimi-ve-veri-yonetimi

Data Augmentation

An approach that expands the training set by transforming existing data to improve model robustness.