PHYS 303 - Bayesian/Deep Learning in Sci.

Unit(s): 4

This course on deep learning and Bayesian data analysis, applicable to all STEM fields, covers deep learning architectures, Bayesian statistics, Hamiltonian Monte Carlo (HMC), latent variables, multi-dimensional optimization, emphasizing concepts that have a connection to physical sciences, such as classical and statistical mechanics. It focuses on deep learning and Bayesian data analysis techniques that are fast, robust, and scalable to high dimensional parameter spaces. We use examples of data analysis applications that are often encountered in the real world of physical sciences.

Prerequisite: (CS 110 and MATH 109) or PHYS 301 or PHYS 302
Corequisite: PHYS-303L
College of Arts and Sciences