Bootcamp Lectures

14 lectures spanning ML fundamentals, molecular representations, deep learning, and LLMs — click any card to view slides, notes, and further reading.

Week 1 · Aug 10 – 14 · Foundations of ML & Representations

Introduction to ML for Chemistry

Bootcamp objectives, logistics, and the landscape of ML in chemical sciences

Jules Schleinitz · Mon Aug 10

Evolution of Molecular Representations

SMILES, InChI, SELFIES, fingerprints, expert-crafted features, molecular graphs

Jules Schleinitz · Mon Aug 10

Supervised Learning: Regression & Classification

Bias-variance, hyperparameter optimization, feature selection, different models

Jules Schleinitz · Tue Aug 11

Neural Networks & Deep Learning

MLPs, backpropagation, Adam, dropout, PyTorch overview

Amin Tavakoli · Tue Aug 11

Graph Neural Networks

Message passing, GCN, GAT, MPNN, PyTorch Geometric

Amin Tavakoli · Wed Aug 12

Model Interpretability

SHAP, LIME, attention maps, concept-based explanations, interpretability in chemistry

Michael Yusov · Wed Aug 12

Learned Representations

Pretraining, fine-tuning, transfer learning for chemical tasks

Chenghao Liu · Thu Aug 13

Diffusion Models

Generative modelling with diffusion; applications in molecular design

Chenghao Liu · Thu Aug 13

Week 2 · Aug 17 – 21 · Dataset Design & LLMs

Self-attention, BERT, ChemBERTa, text-based representations for chemistry

TBD · Mon Aug 17

Active Learning Theory

Query strategies: uncertainty, BALD, core-set, pool-based vs. stream-based

Jules Schleinitz · Mon Aug 17

Bayesian Optimization

Surrogates, EI/UCB/PI, BO loop, molecular & materials discovery, multi-objective BO

TBD · Tue Aug 18

Uncertainty Quantification

Calibration, conformal prediction, ensembles, Bayesian NNs, reliability diagrams

TBD · Tue Aug 18

LLMs as Chemistry Assistants

RAG, tool use, literature extraction, hallucination limits

TBD · Wed Aug 19

Agentic AI for Chemistry

ReAct, Coscientist, multi-agent systems, self-driving laboratories

TBD · Wed Aug 19