16 Structured Probabilistic Models for Deep Learning

16.1 The Challenge of Unstructured Modeling

16.2 Using Graphs to Describe Model Structure

16.2.1 Directed Models

16.2.2 Undirected Models

16.2.3 The Partition Function

16.2.4 Energy-Based Models

16.2.5 Separation and D-Separation

16.2.6 Converting between Undirected and Directed Graphs

16.2.7 Factor Graphs

16.3 Sampling from Graphical Models

16.4 Advantages of Structured Modeling

16.5 Learning about Dependencies

16.6 Inference and Approximate Inference

16.7 The Deep Learning Approach to Structured Probabilistic Models

16.7.1 Example: The Restricted Boltzmann Machine