Inference, Information Theory, Learning and Statistical Mechanics
APPHY 286
Subject & Catalog Number
Course Information
Description
This course focuses on the modern applications of Statistical Mechanics. We will learn the basics of information theory, coding and compression. We will next learn about Bayesian Inference, priors and maximizing entropy, which will naturally lead us to regularization and compressed sensing. We will then cover learning: support vector machines, vc dimension, supervised, reinforcement and unsupervised learning. These topics, which build on each other, will be taught using examples in the primary literature with an emphasis on applying the framework we develop. Applications will be taught through problems in genomics, neuroscience, geophysics, and engineering.
Course Notes
Applied Physics 286 is also offered as Physics 286. Students may not take both for credit.
Recommended Prep
Comfort with Linear Algebra, Calculus is necessary, undergraduate Statistical Mechanics would be useful but not necessary.
Available for Harvard Cross Registration
NOTE: This course requires additional sections; you will be prompted to choose secondary components during the Add to Cart process
