Zahri-Edu University › Graduate & Research

GRAD

Mathematics for Artificial Intelligence

Optimization and gradient methods, neural ODEs and diffusion models, probability for machine learning.

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 · 11 sections

1

Optimisation Theory

  1. 1.1Convex and non-convex optimisation
  2. 1.2Stochastic gradient methods
  3. 1.3Implicit regularisation
2

Approximation Theory

  1. 2.1Universal approximation
  2. 2.2Depth vs width
3

Neural ODEs & Flows

  1. 3.1Continuous-depth models
  2. 3.2Normalising flows
4

Diffusion Models

  1. 4.1Score-based generative modelling
  2. 4.2SDE formulation
5

Symmetry & Geometry in Learning

  1. 5.1Equivariant networks
  2. 5.2Symmetry-driven machine learning