generalization Archives

Regularization discourages a model from fitting training data too narrowly, improving its ability to generalize to new examples.

Jul 8, 2026 by Ethan Caldwell • 1 min read

Dropout regularizes a neural network by randomly disabling some units during training to reduce overreliance and overfitting.

Apr 12, 2026 by Ethan Caldwell • 1 min read

Cross-validation estimates model generalization by training and evaluating repeatedly on different partitions of the available data.

Mar 25, 2026 by Ethan Caldwell • 1 min read

By Marcus Lee Mar 24, 2026 • 1 min read

Double descent is a learning pattern where test error falls, rises near interpolation, and then falls again as model capacity increases.

#Generalization