Statistical Mechanics of Spin Glasses and Neural Networks

Course Number(s): 
Physics 265
Instructor(s): 
School(s): 

Semester: 

  • Spring 2025

Course Level: 

  • Graduate, Undergraduate
Syllabus:  PDF icon Physics 265-2025 Edition .pdf
Class Days/Times: 
Mon 3:00pm to 4:15pm
Wed 3:00pm to 4:15pm
Course Description: 

The theory of random magnetic systems, spin-glasses, has transformed our understanding of the impact of disorder and complexity in many areas such as physics, biology, computer science, statistics, neuroscience, and Artificial Intelligence. The purpose of the course is to survey advanced spin glass theoretical approaches, including Replica Theory, Dynamic Mean Field Theory, the cavity method, and belief propagation. Applications include the physics of spin glasses, random matrices, chaos in random recurrent networks, associative memory, learning in deep neural networks, and Artificial Intelligence.