Zahri-Edu University › Mathematics for Machine Learning & AI

AI 101

Mathematical Foundations of Machine Learning & AI

The mathematics behind modern AI in one course: learning as optimization, generalization, linear and logistic models, neural networks and backpropagation.

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

7 chapters · 22 sections

1

Learning from Data

  1. 1.1Supervised and unsupervised learning
  2. 1.2Empirical risk minimisation
  3. 1.3Loss functions
2

Linear Models

  1. 2.1Linear regression
  2. 2.2Logistic regression
  3. 2.3Regularisation
3

Optimisation

  1. 3.1Gradient descent
  2. 3.2Stochastic gradient descent
  3. 3.3Momentum and Adam
4

Neural Networks

  1. 4.1Perceptron
  2. 4.2Multilayer networks
  3. 4.3Activation functions
  4. 4.4Universal approximation
5

Backpropagation

  1. 5.1Computational graphs
  2. 5.2Chain rule in practice
  3. 5.3Automatic differentiation
6

Generalisation

  1. 6.1Bias–variance trade-off
  2. 6.2Overfitting and validation
  3. 6.3Capacity and VC dimension
7

Unsupervised Learning

  1. 7.1k-means
  2. 7.2PCA
  3. 7.3Energy-based models