AI engineering glossary · Deep learning core
What is iteration?
Iteration (also called Training step): One single update step in training: a forward pass, a loss computation, a backward pass and a weight update on one mini-batch. The number of iterations per epoch equals the dataset size divided by the batch size.
Iteration: an example
10,000 samples with batch size 250 mean 40 iterations per epoch, so 10 epochs equal 400 iterations.
Related terms
More Deep learning core terms
- Label smoothing
- LAMB optimiser
- Layer
- Layer normalisation
- Leaky ReLU
- Learning rate finder
- LeCun initialisation
- Linear scaling rule
Where you learn it
Iteration is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.