Glossary Library

Technical GlossaryDeep Learning

Softmax Activation

An output activation that expresses multiclass outputs as a normalized probability distribution.

Softmax activation is one of the standard choices for output layers in multiclass classification problems. It normalizes logits into probability-like values for each class, ensuring that they sum to one. This makes model decisions easier to interpret. It is typically used together with cross-entropy loss and remains a cornerstone of modern classification systems.

You Might Also Like

Explore these concepts to continue your artificial intelligence journey.

Glossary Cover

matematik-istatistik-optimizasyon

Bernoulli Distribution

A discrete distribution that models single-step random experiments with only two possible outcomes.

Glossary Cover

matematik-istatistik-optimizasyon

Cross-Entropy Loss

A core classification loss that measures the mismatch between the true distribution and the model’s predicted probability distribution.

Glossary Cover

matematik-istatistik-optimizasyon

Hinge Loss

A loss function used especially in support vector machines that aims to create a safe margin between classes.