Batch Size
The number of training examples processed together in one iteration before updating model weights.
In more detail
Batch size affects training dynamics and memory requirements. Larger batches reduce noise but require more memory. Smaller batches add noise but enable larger learning rates. Optimal batch size depends on data, task, and hardware.
Examples
- Batch size 32 for small GPUs
- Batch size 256 for large datasets
- Distributed training with gradient accumulation
Related terms
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
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