ECE 59500 - Boltzmann Law: Physics to Machine Learning

Lecture Hours: 3 Credits: 1

This is an experiential learning course.

Counts as:
CMPE Special Content Elective
EE Elective

Experimental Course Offered: Fall 2019

Requisites:
MA 26200 or (MA 26500 and MA 26600)

Requisites by Topic:
Differential Equations and Linear Algebra

Catalog Description:
This course introduces the key concepts of equilibrium statistical mechanics leading to the celebrated Boltzmann law and how it leads to Boltzmann machines and related concepts in modern machine learning. No prior background in statistical mechanics is assumed.

Supplementary Information:
This is a mini-course that runs the last 5 weeks of the semester and corresponds to the end of ECE 50653.

Required Text(s):
  1. Lessons from Nanoelectronics, Part A: Basic Concepts, 2nd Edition, Datta, S., World Scientific, 2017, ISBN No. 13: 978-9813209749.

Recommended Text(s): None.

Learning Outcomes:

A student who successfully fulfills the course requirements will have demonstrated:
  1. Ability to perform advanced semiclassical analysis of devices involving the interconversion of heat and electricity as well as electron interactions.. [1]

Lecture Outline:

Weeks Topic
3 Weeks Key concepts of statistical mechanics: Heat & Electricity, Second Law and Information
1 Week Self-consistent Field Method for Interacting Systems
1 Week Boltzmann Machines