AI engineering glossary · Deep learning core
What is logits?
Logits: The raw, unnormalised scores a network produces just before softmax or sigmoid turns them into probabilities. They can be any real number, and losses are often computed directly from them for better numerical stability.
Logits: an example
A three-class model outputs logits [3.1, -0.5, 0.2]; softmax then converts them into probabilities.
Related terms
More Deep learning core terms
- Loss scaling
- Lottery ticket hypothesis
- LSTM
- Maxout
- Mixed precision training
- Model parallelism
- Multi-task learning
- Multilayer perceptron
Where you learn it
Logits is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.