AI engineering glossary · Deep learning core
What is batch size?
Batch size (also called Mini-batch size): The number of training examples processed together before the weights are updated. Larger batches give smoother gradient estimates and better hardware use but need more memory, while smaller batches add noise that can help generalisation.
Batch size: an example
Setting batch size to 64 on a dataset of 6,400 samples gives 100 updates per epoch.
Related terms
More Deep learning core terms
- bfloat16
- Bias term
- Bidirectional RNN
- Binary cross-entropy
- Bottleneck
- Catastrophic forgetting
- Cell state
- Checkpoint
Where you learn it
Batch size is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.