AI.info
Classical machine learning
The models that still win on tabular data, and the structured assumptions each one smuggles in.
- Classical Models as Structured Biases
- The Tabular Data Contract
- Pipelines, Baselines, and Preprocessing Boundaries
- Linear Regression Fundamentals
- Regression Diagnostics and Assumptions
- Ridge, Lasso, and Elastic Net
- Robust, Quantile, and Count Regression
- Logistic Regression Explained
- Multiclass, Ordinal, and Thresholded Decisions
- Linear and Quadratic Discriminant Analysis
- K-Nearest Neighbors: Local Learning
- Distance, Scaling, and the Curse of Dimensionality
- Naive Bayes Classifiers
- Decision Trees: Recursive Partitioning
- Tree Pruning, Instability, and Missing Data
- Bagging and Random Forests
- Out-of-Bag Evaluation and Forest Interpretation
- Support Vector Machines: Margins and Soft Constraints
- Kernels and Nonlinear Decision Boundaries
- Splines, Basis Expansions, and Generalized Additive Models
- Kernel Ridge and Gaussian Process Regression
- Feature Engineering and Interaction Design
- Categorical, Missing, and Sparse Data
- Imbalanced Data, Costs, and Rare Events
- Calibration, Uncertainty, and Abstention
- Interpreting Classical Models Without Fooling Yourself
- Efficiency, Scaling, and Deployment Trade-Offs
- Model Selection and Error Analysis
- Capstone: Build and Defend a Classical ML System