thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Foundational

Batch Size

The number of training examples processed together before the model's parameters are updated.

Definition

Larger batches use GPU parallelism efficiently and give smoother gradients but need more memory and may generalize slightly worse; smaller batches are noisier and slower per epoch. Gradient accumulation simulates large batches on limited memory. Inference servers also batch requests to raise throughput.

Exam tip

Out-of-memory errors during training are often fixed by reducing batch size or using gradient accumulation.

Related terms