Losses and objectives · MLD-0616
L2 loss
A loss based on squared Euclidean differences, with scaling conventions varying by context.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Compare predicted and target vectors.
Original caveat
A prediction loss differs from a penalty on weights.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: ML · DL · SLM · LLM.
Aliases: Squared-error loss.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- scikit-learn: evaluation metrics ↗ · Reference link
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗