Tag: ml-foundations
Concepts
- Asymmetric Loss Functions
- The Bias-Variance Decomposition
- Cross-Entropy and Log Loss
- Discriminative vs Generative Models
- Focal Loss
- Hinge Loss and Margin Maximization
- Hyperparameters vs Parameters
- Hypothesis Space and Inductive Bias
- Inductive vs Transductive Learning
- Interpolation vs Extrapolation
- Irreducible Error and the Bayes Rate
- Learning Paradigms Compared
- Machine Learning vs Classical Statistics
- Model Capacity and Complexity Control
- Model Complexity vs Inference Cost
- Negative Log-Likelihood as a Loss Function
- Objective Functions vs Evaluation Metrics
- Parametric vs Nonparametric Models
- Signal-to-Noise Ratio and Learnability
- The Bayes Optimal Classifier
- The IID Assumption and When It Breaks
- The Normal Equations vs Iterative Solvers
- The Pinball Loss
- The Regularization Path
- Training Error vs Generalization Error