Plans for the week of April 13-17
Dear all, welcome back to FYS5429/9429.
The plans this week are (and please use just the jupyter-notebook at https://github.com/CompPhysics/AdvancedMachineLearning/blob/main/doc/pub/week12/ipynb/week12.ipynb)
Plans for the Week of April 13–17, 2026
Generative methods, energy-based models, and Boltzmann machines.
Recap:?Energy-based models and the partition function
MCMC and Gibbs sampling?— the engine behind RBM training
Boltzmann machines?— theory, binary-binary and Gaussian-binary RBMs
Hands-on RBM implementations?— pure NumPy and PyTorch
XOR parity problem
2-spin Ising model: learning the coupling?
NumPy vs PyTorch comparison
Variational Autoencoders (VAEs)?— mathematical foundations and ELBO
Jupyter notebooks:
https://github.com/CompPhysics/QuantumComputingMachineLearning/tree/gh-pages/doc/pub/week12/ipynb/week12.ipynb
Reading recommendations
Boltzmann machines: Goodfellow et al chapters 18.1-18.2, 20.1-20-7; To create Boltzmann machine using Keras, see Babcock and Bali chapter 4, see?https://github.com/PacktPublishing/Hands-On-Generative-AI-with-Python-and-TensorFlow-2/blob/master/Chapter_4/models/rbm.py
More on Boltzmann machines: see also Foster, chapter 7 on energy-based models at?https://github.com/davidADSP/Generative_Deep_Learning_2nd_Edition/tree/main/notebooks/07_ebm/01_ebm
VAEs: Goodfellow et al, for VAEs see sections 20.10-20.11
See you all soon,
Morten, Oda and Ruben