Bootcamp Lectures

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

Watch all 14 recordings on YouTube

Week 1 · Foundations of ML & Representations

Lecture Bootcamp Introduction
Bootcamp objectives, logistics, and the landscape of ML in chemical sciences
Jules Schleinitz
→
Lecture Evolution of Molecular Representations
SMILES, InChI, SELFIES, fingerprints, expert-crafted features, molecular graphs
Jules Schleinitz
Companion tutorial
→
Lecture Supervised Learning: Regression & Classification
Bias-variance, hyperparameter optimization, feature selection, different models
S. Wahler
Companion tutorial
→
Lecture Neural Networks & Deep Learning
MLPs, backpropagation, Adam, dropout, PyTorch overview
Jules Schleinitz
Companion tutorial
→
Lecture Machine-Learned Interatomic Potentials (MLIP)
Message passing, GCN, GAT, MPNN, PyTorch Geometric
Madeline Murphy
Companion tutorial
→
Lecture Model Interpretability
Interpretable-by-design vs. post-hoc: MDI, permutation importance, ICE/PDP, LIME, and SHAP
Michael Yusov
Companion tutorial
→
Lecture Data Stewardship
Data management in experimental projects for efficient use in data-driven projects
Alix Schmidt
Companion tutorial
→
Lecture Learned Representations
Pretraining, fine-tuning, transfer learning for chemical tasks
Jules Schleinitz
Companion tutorial
→
Lecture Generative Models
Generative modelling with diffusion; applications in molecular design
Chenghao Liu
Companion tutorial
→

Week 2 · Dataset Design & LLMs

Lecture Design of Experiments (DOE)
Factorial design, screening, response surfaces, and experimental planning strategies
Alix Schmidt
Companion tutorial
→
Lecture Active Learning Theory
Query strategies: uncertainty, BALD, core-set, pool-based vs. stream-based
Jules Schleinitz
Companion tutorial
→
Lecture Bayesian Optimization
Surrogates, EI/UCB/PI, BO loop, molecular & materials discovery, multi-objective BO
Jules Schleinitz
Companion tutorial
→
Lecture Retrieval-Augmented Generation (RAG)
RAG, tool use, literature extraction, hallucination limits
S. Wahler
Companion tutorial
→
Lecture Agentic AI for Chemistry
ReAct, Coscientist, multi-agent systems, self-driving laboratories
B. Reiner | J. Wade
Companion tutorial
→