Deep Learning meets Physics: Restricted Boltzmann Machines Part I

Theory behind Restricted Boltzmann Machines — A powerful Tool for Recomender Systems

Artem Oppermann
Towards Data Science

This tutorial is part one of a two part series about Restricted Boltzmann Machines, a powerful deep learning architecture for collaborative filtering. In this part I introduce the theory behind Restricted Boltzmann Machines. The second part consists of a step by step guide through a practical implementation of a model which can predict whether a user would like a movie or not.

The practical part is now available here.

Table of Contents:

  • 0. Introduction
  • 1. Restricted Boltzmann Machines
  • 1.1 Architecture
  • 1.2 An Energy-Based-Model
  • 1.3 A probabilistic Model
  • 2. Collaborative Filtering with Restricted Boltzmann Machines
  • 2.1 Recognizing Latent Factors in The Data
  • 2.2 Using Latent Factors for Prediction
  • 3. Training
  • 3.1 Gibbs Sampling
  • 3.2 Contrastive Divergence

If you liked the article and want to share your…

Create an account to read the full story.

The author made this story available to Medium members only.
If you’re new to Medium, create a new account to read this story on us.

Or, continue in mobile web

Already have an account? Sign in

Responses (12)