print, pdf


print, pdf

Linear Algebra

pdf, print

Machine Learning

To be written!
  • 1. The Pseudoinverse - Linear Regressor; Polynomial Regressor; Linear Combination of Nonlinear Functions; Logistic Regressor; Pitfalls.
  • 2. Gradient Descent - Partial Derivatives and the Gradient; Algebraic Functions; Non-Algebraic Functions; Linear Regressor; Logistic Regressor; Logistic Classifier; Pitfalls.
  • 3. Non-Parametric Models - K-Nearest Neighbors; Decision Trees; Random Forests.
  • 4. Validation - Overfitting, Underfitting, and the Bias-Variance Tradeoff; Cross-Validation; Normalization; Feature Selection.
  • 5. Neural Networks - Multivariable Chain Rule; Forward Propagation, Activation Functions, and Weight Updates; Computing Gradients via Chain Rule; Computing Gradients via Path Enumeration; Computing Gradients via Backpropagation.
  • 6. Bayesian Methods - Probability Distributions; Bayes' Theorem; Maximum Likelihood; Naive Bayes; Prior and Posterior Distributions; Maximum a Posteriori.
  • 7. Unsupervised Learning - K-Means Clustering; Principal Component Analysis.