ECE 50633 - Boltzmann Law: Physics to Machine Learning
This is a 5-week that corresponds to the end of ECE 50653.
Lecture Hours: 3 Credits: 1
Areas of Specialization:
- Microelectronics and Nanotechnology
- EE Elective
- CMPE Special Content Elective
Each Fall, Spring
On-campus and online
MA 26200 or (MA 26500 and MA 26600)
Requisites by Topic:
Differential Equations and Linear Algebra
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.
- Lessons from Nanoelectronics, Part A: Basic Concepts (full text provided in Brightspace) , 2nd Edition , Datta, S. , World Scientific , 2017 , ISBN No. 13: 978-9813209749
A student who successfully fulfills the course requirements will have demonstrated an ability to:
- Explain the law of equilibrium and entropy
- Explain how Boltzmann machines operate.
- Explain how quantum circuits operate.
|Week 1||Boltzmann Law: State Space, Boltzmann Law, Shannon Entropy, Free Energy, Self-Consistent Field|
|Week 2||Boltzmann Machines: Sampling, Orchestrating Interactions, Optimization, Inference, Learning|
|Week 3||Transition Matrix: Markov Chain Monte Carlo, Gibbs Sampling, Sequential versus Simultaneous, Bayesian Networks, Feynman Paths|
|Week 4||Quantum Boltzmann Law: Quantum Spins, One Q-Bit System, Spin-Spin Interactions, Two Q-Bit Systems, Quantum Annealing|
|Week 5||Quantum Transition Matrix: Adiabatic To Gated Computing, Hadamard Gates, Grover's Search, Shor's Algorithm, Feynman Paths|
Students in this course will be evaluated by exams. (3/2022)