What is Learning Rate?

A vector showing how much each parameter should change to reduce loss.

A configuration value set before training, such as learning rate, batch size, or depth.

How well a model performs on new, unseen data outside the training set.

Methods that adapt models by training a small subset of added parameters.

A decoding algorithm that keeps the top several candidate sequences at each step to find higher-probability outputs.

A mathematical objective that quantifies prediction error during training.