Machine learning for physicists

1. Overview
   • Scientific machine learning with and without data
2. Machine learning practices
   • Hello world example: Hand-written digits recognition
   • Programming frameworks, hardware, and workflow
3. A hitchhiker’s guide to deep learning
   • The four pillars: data, model, loss function, and optimization
   • Deep learning primitives: CNN, GNN, and transformer
4. Symmetries in machine learning
   • Invariant and equivariant neural networks
   • DeepMD, Euclidean equivariant GNN, Tensor field networks
   • Permutation symmetry and quantum wavefunctions
5. Differentiable programming
   • The engine of deep learning: automatic differentiation on computation graphs
   • Differentiable DFT/MD/Tensor networks/..., and why they are useful
6. Generative models-I
   • A dictionary of generative models and statistical physics
   • Boltzmann machines
   • Autoregressive models
   • Variational autoencoders
7. Generative models-II
   • Normalizing flows
   • Diffusions models
   • Applications of generative models to many-body problems
   • The Universe as a generative model
8. Wrap up
   • AI for science: why now?

Title image generated by stable diffusion with the prompt: "a tile image for the course on 'Machine learning for physicists', eye-catching, artist style with sci-fi feeling". (Yes, “tile” instead of "title" :P)