https://github.com/arn4/colloquio

4th year seminar @ SNS
https://github.com/arn4/colloquio

Last synced: 3 months ago
JSON representation

4th year seminar @ SNS

• Host: GitHub
• URL: https://github.com/arn4/colloquio
• Owner: arn4
• Created: 2021-03-15T11:46:52.000Z (over 5 years ago)
• Default Branch: main
• Last Pushed: 2021-06-10T15:51:06.000Z (about 5 years ago)
• Last Synced: 2025-12-31T17:53:00.205Z (6 months ago)
• Language: TeX
• Homepage:
• Size: 49.6 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Unsupervised Learning with Restricted Boltzmann Machines

![Build LaTeX documents](https://github.com/arn4/colloquio/workflows/LaTeX%20documents/badge.svg)

![Compile C++](https://github.com/arn4/colloquio/workflows/C++/badge.svg)

This is the repository of my 4th-year-seminar (a.k.a. *colloquio*) at Scuola Normale Superiore.

The purpose of this seminar is to illustrate the operation of Restricted Boltzmann Machines and some classical algorithms to train them.

In addition, an alternative algorithm proposed by Gabriè [[1]](#1) is analyzed; it is based on the mean field theory of the Ising model.

All the discussed algorithms have been implemented and tested in C++.

## Documents

These are the last avaible versions of:

  - [**Slides**](https://uz.sns.it/~arna/static_/ext_files/colloquio/slides-handout.pdf) slides used during the presentation ([version with timing](https://uz.sns.it/~arna/static_/ext_files/colloquio/slides.pdf))

  - [**NoteBook**](https://uz.sns.it/~arna/static_/ext_files/colloquio/notebook.pdf) personal notes and transcription from the papers that I need for prepare the talk.

### References

[1] 

Gabrié M., Tramel E.W. and Krzakala F., 2015, December.  

_Training restricted Boltzmann machines via the Thouless-Anderson-Palmer free energy._  

In Proceedings of the 28th International Conference on Neural Information Processing Systems-Volume 1 (pp. 640-648).