ECE544: Pattern Recognition (Fall 2025)

Course Information

The goal of Pattern Recognition is to find structure in data. In this course we will cover three main areas, (1) discriminative models, (2) generative models, and (3) reinforcement learning models. In particular we will cover the following: linear regression, logistic regression, support vector machines, deep nets, structured methods, learning theory, kMeans, Gaussian mixtures, expectation maximization, VAEs, GANs, Markov decision processes, Q-learning and Reinforce.

Pre-requisites: ECE313: Probability with engineering applications (or equivalent), MATH257: Linear Algebra with Computational Applications (or equivalent), and proficiency in Python.

Recommended Text:
(1) Patterns, Predictions, and Actions: Foundations of Machine Learning by Moritz Hardt and Benjamin Recht
(2) Pattern Recognition and Machine Learning by Christopher Bishop
(3) Machine Learning: A Probabilistic Perspective by Kevin Murphy
(4) Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville 
(5) Graphical Models by Nir Friedman and Daphne Koller
(6) Reinforcement Learning by Richard Sutton and Andrew Barto

Course Deliverables:
(1) Homeworks: There will be approximately bi-weekly problem sets assigned up to transition to the final project; they include both standard and computational problems. Solutions will be posted on the course website. 
(2) Exam: There will be an exam scheduled tentatively for November 18.
(3) Literature review on a published paper related to the course topics. The paper is chosen by students and should be cleared by course instructors. The article will serve as the starting point for the formation of the final project.
(4) Final Project: Based on the chosen topic in (3); provide a writeup and a presentation describing your project, the approach, and the results.

Grading:

40% Homeworks; 20% Exam; 10% Literature review; 30% Final Project

Exam: In class, Date: November 11, 11am-12:20pm.

Lectures

The syllabus is subject to minor changes.