Zahri-Edu › Math-University › Mathematics for Machine Learning & AI

AI 112

Multivariable Calculus for Machine Learning

Gradients, Jacobians and Hessians, the chain rule on computational graphs, automatic differentiation and Taylor approximations of loss functions.

In preparation

The lecture notes for this course are being written. Below is the planned table of contents; chapters will be published one by one.

Table of contents

5 chapters · 12 sections

1

Functions of Several Variables

  1. 1.1Partial derivatives
  2. 1.2Gradient and directional derivatives
2

Jacobians & Hessians

  1. 2.1Jacobian matrix
  2. 2.2Hessian and curvature
  3. 2.3Taylor expansion in several variables
3

The Chain Rule

  1. 3.1Multivariable chain rule
  2. 3.2Computational graphs
4

Automatic Differentiation

  1. 4.1Forward mode
  2. 4.2Reverse mode (backpropagation)
5

Optimality

  1. 5.1Critical points
  2. 5.2Convex functions
  3. 5.3Constrained optimisation and Lagrange multipliers