Concept dictionary
Batch
A batch is a group of examples or requests processed together, often to make training or inference more efficient.
- Review state
- Reviewed in POC
- Freshness
- Current
- Version
- 2
Also called
- Batch
- Training Batch
Remember it this wayOne batch, one parameter update.
In plain language
A batch is the set of examples a training process handles before it updates a model’s parameters. Batch size is the number of examples in that set.
Why it matters
Batch size affects memory use, training speed, and the variability of each update. It is a training choice, not just a way to organize files.
Example
With a batch size of 32, the system processes 32 training examples, calculates their combined loss, and then updates the model once.
Common misconception
A batch is not the entire dataset unless full-batch training is being used. Most modern training uses many smaller batches during each epoch.
Related terms
Sources
- Google for Developers, “Machine Learning Glossary”provides established boundaries for core machine-learning vocabulary.
Learn more
- Compare [[training|Training]], [[epoch|Epoch]], [[dataset|Dataset]], and [[loss-function|Loss Function]] to place Batch in the surrounding system.
- Follow the cited source material above for the method, standard, or research context behind this draft.