Mathematical Foundations for Machine Learning

20 lectures

Linear algebra, calculus, and probability you need to read ML papers with confidence.

01Lecture 01 · Introduction to Linear Algebra

02Lecture 02 · Solving Systems of Linear Equations

03Lecture 03 · Groups, Vector Spaces, and Linear Combinations

04Lecture 04 · Vector Spaces, Linear Independence, Basis and Dimension

05Lecture 05 · Dot Products and Inner Products

06Lecture 06 · Eigenvalues, Eigenvectors, and Determinants

07Lecture 07 · Matrix Decompositions, Vector Spaces, and Determinants

08Lecture 08 · Singular Value Decomposition and Vector Calculus

09Lecture 09 · Gradients, the Jacobian, and Taylor Series

10Lecture 10 · Taylor Series and Hessian-Based Optimization

11Lecture 11 · Gradient Descent

12Lecture 12 · Challenges of Gradient Descent and Constrained Optimization

13Lecture 13 · Gradient Descent Optimization

14Lecture 14 · Gradient Descent Variants and Constrained Optimization

15Lecture 15 · Constrained Optimization and Duality

16Lecture 16 · Principal Component Analysis

17Lecture 17 · Principal Component Analysis — Practical Computation and the Dual Perspective

18Lecture 18 · Quadratic Programming and the KKT Conditions

19Lecture 19 · Support Vector Machines — Hard Margin Classifier

20Lecture 20 · Support Vector Machines

Loading comments…