Contents.md

Course Contents

1. Introduction

   • Overview
   • Expectations and assessments
   • Exercise: Getting started

2. Machine Learning Basics

   • Terminology
   • Learning by example
     • Supervised
     • Unsupervised
     • Reinforcement
   • Exercise: Crystal hardness

3. Materials Data

   • Data sources and formats
   • API queries
   • Exercise: Data-driven thermoelectrics

4. Crystal Representations

   • Compositional
   • Structural
   • Graphs
   • Exercise: Crystal space

5. Classical Learning

   • k-nearest neighbours
   • k-means clustering
   • Decision trees and beyond
   • Exercise: Metal or insulator?

6. Artificial Neural Networks

   • From neuron to perceptron
   • Network architecture and training
   • Convolutional neural networks
   • Exercise: Learning microstructure

7. Building a Model from Scratch

   • Data preparation
   • Model choice
   • Training and testing
   • Exercise: Crystal hardness II

8. Accelerated Discovery

   • Automated experiments
   • Bayesian optimisation
   • Reinforcement learning
   • Exercise: Closed-loop optimisation

9. Generative Artificial Intelligence

   • Large language models
   • From latent space to diffusion
   • Exercise: Research challenge

10. Recent Advances

    • Guest lecture
    • Exercise: Research challenge