EE 171 - Introduction to Machine Learning for Electrical Engineers

Introduction to machine learning with hardware implementation. Topics include linear algebra and probability review, linear regression, multilayer perceptrons, stochastic gradient descent, and convolutional neural networks. Includes hands-on lab component in which students train neural networks using Keras and deploy the models to Field Programmable Gate Arrays (FPGAs).

Prerequisite(s): EE 102 (may be taken concurrently) and EE 118 (with grade of “C-” or better).
Grading: Letter Graded

Class Schedule | Syllabus Information | University Bookstore