Batch
ELI5 — The Vibe Check
A batch is a small group of training examples that the model processes at once before updating its weights. Instead of learning from examples one at a time (slow) or all at once (doesn't fit in memory), you feed it in batches. Batch size is a hyperparameter — bigger batches are faster but sometimes learn worse. AI loves batches.
Real Talk
A batch is a subset of training examples processed together in a single forward and backward pass. Batch size is a key hyperparameter: larger batches provide more stable gradient estimates but require more memory and can hurt generalization; smaller batches introduce noise that can be regularizing. Mini-batch gradient descent is the standard training approach.
When You'll Hear This
"Set batch size to 32." / "Out of memory — reduce the batch size."
Related Terms
Epoch
An epoch is one complete pass through your entire training dataset. If you have 100,000 examples, one epoch means the model has seen all 100,000 once.
Gradient Descent
Gradient Descent is how an AI learns — it's the algorithm that nudges the model's weights in the right direction after each mistake.
Hyperparameter
Hyperparameters are the settings you configure BEFORE training starts — as opposed to parameters (weights) which the model learns ON ITS OWN.
Loss Function
The loss function is the AI's score of how badly it's doing.
Training
Training is the long, expensive process where an AI learns from data.