Batch Normalization (BatchNorm) is a technique that stabilizes and accelerates neural network training by normalizing layer activations. It adjusts activations to have zero mean and unit variance within each mini-batch, followed by learnable scaling and shifting parameters. BatchNorm reduces internal covariate shift, allowing higher learning rates and mitigating issues like vanishing/exploding gradients. It also acts as a form of regularization, often reducing the need for dropout in deep networks.