Deep Learning meets Physics: Restricted Boltzmann Machines Part I
Theory behind Restricted Boltzmann Machines — A powerful Tool for Recomender Systems
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