This course is designed to provide students with a thorough understanding of the mathematical underpinnings of neural networks and graphical models, as well as the implementation and testing of various forms of neural networks and graphical models in software.

ECE6141 Fall 2018 Lectures 1-2 | Introduction & Course Overview |ECE6141 Fall 2018 Lectures 1 and 2    ECE6141 Problem Set 1    Solutions Problem Set 1

Lecture 3 | Bayesian Decision Theory |ECE6141 Fall 2018 Lecture 3    ECE6141 Problem Set 2     Solutions Problem Set 2

Lectures 4-5 | ML and Bayesian Learning, Density Estimation, Gaussian Mixtures, EM and
Variational Bayesian Inference, Performance Assessment of Classifiers |ECE6141 Fall 2018 Lectures 4 and 5.ppt   ECE6141 Problem Set 3    Solutions Problem Set 3

Lecture 6-7 | Logistic Regression & Decision-based Learning (Perceptrons) & Decision Trees |ECE6141 Fall 2018 Lectures 6 and 7    ECE6141 Problem Set 4    Solutions Problem Set 4

Lecture 8 | Regression Based Learning and Support Vector Machines | ECE6141 Fall 2018 Lecture 8

Lecture 9-10 | Multiple Layer Perceptrons, Deep Network Learning & Boosting | ECE6141 Fall 2018 Lectures 9 and 10    ECE6141 Problem Set 5    Solutions Problem Set 5

Lecture 11 | Radial Basis Functions, Gaussian Processes, Relevance Vector Machines, Feature
Selection, Dimensionality Reduction, LVQ & Information-theoretic Co-clustering | ECE6141 Fall 2018 Lecture 11

Lecture 12 | Markov and Hidden Markov Models | ECE6141 Fall 2018 Lecture 12

Lecture 13 | Graphical Models & Bayesian Inference Networks | ECE6141 Fall 2017 Lecture 13      ECE6141 Fall 2018 Take Home Exam    ECE6141 Fall 2018 Take Home Exam Solutions

ECE6141 Course Outline Fall 2018