All glossary terms
conceptsintermediate

Softmax

An activation function that converts model outputs to probability distributions across classes.

In more detail

Softmax normalizes logits to probabilities summing to 1. Used as the output layer for multi-class classification. Paired with cross-entropy loss for training. Enables probabilistic interpretation of model predictions.

Examples

  • Image classification with multiple classes
  • Multi-class text classification
  • Intent classification in NLU

Related terms

Activation Function
Professional AI/ML Bootcamp · Starts 2nd January, 2027

Ready to Build Production AI Systems?

Join a small cohort learning directly from an engineer who's shipped AI at Atlassian and PhonePe scale.

20 weeks · Weekend live classes · 1:1 mentorship · 20+ projects.

20 Weeks

Live Weekend Classes

< 30 Seats

Small Batch

Batch Full

Next Soon

Get priority access

7-Day

Money-Back Guarantee

Taught by Debasish Maji · Senior AI Engineer · Ex-Atlassian (Rovo Agent) · Ex-PhonePe (550M+ users)

Get notified when the next batch opens + free AI resources