Basic Stucture

The Basis for this course is to learn about complex stochastic models, and how they can be used to learn from data. We will learn about stochastic modeling techniques and their deterministic counterparts.

All models are wrong, but some are useful

-G. E. P. Box

Topics to be discussed in this course follow as:

• Markov Models
• Markov Random Fields
• The Ising Model

• Markov Chain Monte Carlo for models with intractable normalizing constants

• Point Process Models
• Gaussian Processes
• Spatial and Temporal Models
• Social Networks
• Branching Processes
• Epidemic Models

Many examples will be centered around the above. You will learn how to combine the models above in order to explain the relationships in complex data. Additionally, you will spend an extensive amount of time learning and implementing the computational procedures required for inferring from such models.

Much of the course is devoted to the final course project. In this project, you will write a paper that is of publishable quality for: either stochastic modeling, inference, computation, or any combination of the three.