Brown CS 242

Probabilistic Graphical Models, Fall 2016.

Course Calendar

Download lecture slides by clicking on the corresponding lecture title. Lecture topics (right) link to suggested readings below.

No Lecture

October 11, 2016

Begin to form your project team & define your project area.

(No Lecture)

November 24, 2016

Project Presentations

December 13, 2016

Beginning at 2:30pm in CIT 368.

Suggested Readings

We provide suggested readings from several sources. You do not need to read all of them. Instead, we suggest you compare various options, and choose the resource whose style you like best. Barber's Bayesian Reasoning and Machine Learning is freely available online, and is a good place to start.

Acronyms for Primary Resources

Graphical Model Tutorials

Directed & Undirected Graphs: Factorization & Markov Properties

Inference via Variable Elimination

Inference via Belief Propagation: Sum-Product & Max-Product

Inference via Junction Tree Propagation

Exponential Family Distributions: Learning & Inference

Learning (Directed & Undirected) Graphical Model Parameters

Learning via the Expectation Maximization (EM) Algorithm

Learning (Directed & Undirected) Graphical Model Structure

Inference & Learning for Gaussian Graphical Models

Monte Carlo Methods: Rejection & Importance Sampling

Particles & Sequential Monte Carlo

Markov Chain Monte Carlo (MCMC): Gibbs & Metropolis-Hastings

Variational Methods: Naive & Structured Mean Field

Variational Methods: Bethe Approximations, Loopy & Reweighted BP

Discriminative Learning: Conditional Random Fields & Structural SVMs

Neural Networks & Deep Learning

Bayesian Nonparametrics: Dirichlet Processes