Loss Functions
← Back to Neural Network Fundamentals
Functions that measure how far the model’s predictions are from the true values. The loss is what backpropagation minimizes during training.
Key Types
- Cross-Entropy — standard for classification (binary and multi-class)
- MSE (Mean Squared Error) — standard for regression
- Hinge Loss — used in SVMs, margin-based
- Contrastive Loss — for learning embeddings and similarity
Related
- Backpropagation (computes gradients of loss)
- Optimizers (minimize the loss)