Losses and objectives · MLD-1010
Regularization loss
A penalty added to discourage selected model properties.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Penalize large weights.
Original caveat
A penalty can improve generalization while worsening training fit.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: ML · DL · SLM · LLM.
Aliases: None recorded.
Related concepts
Original references
- Deep Learning: online textbook ↗ · Consulted
- scikit-learn: evaluation metrics ↗ · Reference link
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗