Machine learning for physicists
PHYS-467
2025 | Exercise 13: Restricted Boltzmann Machines
This page is part of the content downloaded from 2025 | Exercise 13: Restricted Boltzmann Machines on Sunday, 25 January 2026, 03:21. Note that some content and any files larger than 50 MB are not downloaded.
Description
In this tutorial you will analyse a labelled dataset of real proteins. You will create a generative model trying to approximate the probability distribution of these real data and generate new proteins.
You will test 3 different models and compare their quality: an independent-fields one, a Boltzmann machine and a Restricted Boltzmann Machine.
All credits for the dataset are given to the authors of the following article:
https://www.science.org/doi/10.1126/science.aba3304