5 docs tagged with "classification"

Binary classification with a linear score, sigmoid probability, log loss, and chain-rule parameter gradients.

Forward propagation, backpropagation, and parameter updates in a one-hidden-layer classifier.

Distinguish three model roles by their inputs, outputs, and training objectives, and understand why a BERT architecture alone does not confer retrieval or decision-making ability.

Gaussian generative classifiers whose shared or class-specific covariance assumptions produce linear or quadratic decision boundaries.

Multiclass linear classification with logits, softmax probabilities, cross-entropy, and clear boundaries around multilabel tasks.