Boltzmann Law: Physics to Computing - ECE50633
This course is intended to be broadly accessible to students in any branch of science or engineering who would like to learn about the conceptual framework for equilibrium statistical mechanics and its application to modern machine learning.
Credit Hours: 1
Instructor(s): Supriyo Datta
Phone: (765) 414-5633
Email: datta@purdue.edu
Office: EE 325
Web: Instructor Homepage
Learning Objective:
- Explain the law of equilibrium and entropy
- Understand the operation of Boltzmann machines
- Understand the operation of quantum circuits
Description:
This course is intended to be broadly accessible to students in any branch of science or engineering who would like to learn about the conceptual framework for equilibrium statistical mechanics and its application to modern machine learning. Weekly topics: 1) Boltzmann Law; 2) Boltzmann Machines; 3) Transition Matrix; 4) Quantum Boltzmann Law; 5) Quantum Transition Matrix
Topics Covered:
Key concepts of statistical mechanics, self-consistent field method for interacting systems, Boltzmann machines
Prerequisites:
This course is designed for students who have an undergraduate degree in engineering or the physical sciences, having a familiarity with differential equations and linear algebra.
Applied / Theory:
10 / 90
Exams:
Three exams