Generative AI and LLM glossary

Regularization

A regularization technique used to prevent overfitting in neural networks by randomly deactivating a fraction of neurons during training.

Machine Learning

A technique used to prevent overfitting by adding a penalty for larger coefficients in a model.

Modeling

A modeling error that occurs when a model learns noise and details from the training data.

Modeling

A technique used to prevent overfitting by adding a penalty to the loss function.

Model Evaluation

Variance measures a model's sensitivity to fluctuations in the training data, contributing to overfitting when high.