ECE544NA: Pattern Recognition (Fall 2018)
Course Information
ECE 544NA is a special topics course in pattern recognition, and content varies every year. In Fall 2018, the course will cover three main areas, (1) disciminative models, (2) generative models, and (3) reinforcement learning. See course syllabus for more details.The goal of the course is to provide an understanding of recent research topics in pattern recognition. After having completed the class, students should be familiar with the underlying theory and software that is frequently used in publications related to pattern recognition.
Presentation Schedule: The final presentation schedule is available here.
Pre-requisites: Probability, linear algebra, and proficiency in Python, MATLAB or equivalent.
Recommended Text: (1) Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville, (2) Pattern Recognition and Machine Learning by Christopher Bishop, (3) Graphical Models by Nir Friedman and Daphne Koller and (4) Machine Learning: A Probabilistic Perspective by Kevin Murphy.
Grading: Scribing 33%, final project 33%, final exam 34%. Weights might get adjusted during the course.
Late Policy: No late submission will be accepted after the due date.
Problem Sets: Download the problem sets here and the solution here.
Final Exam: **Two hour exam** Time: 8:00AM-11:00AM, Dec 19 2018. Room: ECEB 1013 & ECEB 1015. Please arrive in the assigned room (TBA) at 8:00AM on time.
Instructor & TAs
Alexander Schwing
InstructorEmail: aschwing[at]illinois.edu
Office Hour: Tues. 13:00-14:00PM
Room: CSL 103
Website: [link]
Yuan-Ting Hu
Teaching AssistantEmail: ythu2[at]illinois.edu
Office Hour: Wed. 15:00-16:00PM
Room: ECEB 2013
Website: [link]
Safa Messaoud
Teaching AssistantEmail: messaou2[at]illinois.edu
Office Hour: Wed. 15:00-16:00PM
Room: ECEB 2013
Website: [link]
Lectures
The syllabus is subject to change.
Event | Date | Description | Materials | Scribes | ||
---|---|---|---|---|---|---|
Lecture 1 | Aug. 28 | Intro/Nearest Neighbor | [Link] | |||
Project Assigned | Aug. 28 | Final Project Instructions | ||||
Lecture 2 | Aug. 30 | Linear Regression | [Link] | [Scribe1] | [Scribe2] | [Scribe3] |
Lecture 3 | Sep. 4 | Logistic Regression | [Link] | [Scribe1] | [Scribe2] | |
Lecture 4 | Sep. 6 | Optimization Primal | [Link] | [Scribe1] | [Scribe2] | |
Lecture 5 | Sep. 11 | PyTorch Tutorial 1 | [Link] | [Scribe1] | [Scribe2] | |
Lecture 6 | Sep. 13 | PyTorch Tutorial 2 | [Link] | |||
Lecture 7 | Sep. 18 | Optimization Dual | [Link] | [Scribe1] | [Scribe2] | |
Lecture 8 | Sep. 20 | SVM | [Link] | [Scribe1] | [Scribe2] | |
Lecture 9 | Sep. 25 | Multiclass Classification and Kernel Methods | [Link] | [Scribe1] | [Scribe2] | |
Lecture 10 | Sep. 27 | Deep Nets 1 (Layers) | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 11 | Oct. 2 | Deep Nets 2 (Backprop) | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2]
[Scribe5] |
[Scribe3] |
Project Due | Oct. 2 | Project Propsal Due | ||||
Lecture 12 | Oct. 4 | Structured Prediction (exhaustive search, dynamic programming) | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 13 | Oct. 9 | Structured Prediction (ILP, LP relaxation) | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 14 | Oct. 11 | Learning in Structured Models | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 15 | Oct. 16 | Review | [Link] | |||
Lecture 16 | Oct. 18 | k-Means | [Link] | [Scribe1] | [Scribe2] | [Scribe3] |
Lecture 17 | Oct. 23 | GMMs | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 18 | Oct. 25 | Expectation Maximization | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 19 | Oct. 30 | Hidden Markov Models | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 20 | Nov. 1 | Variational Auto-Encoders | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2]
[Scribe5] |
[Scribe3] |
Lecture 21 | Nov. 6 | Generative Adversarial Nets | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2]
[Scribe5] |
[Scribe3] |
Lecture 22 | Nov. 8 | Autoregressive Methods and Graph Convolutional Nets | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 23 | Nov. 13 | MDP | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 24 | Nov. 15 | Q-Learning | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
No Lecture | Nov. 20 | Thanksgiving Break | ||||
No Lecture | Nov. 22 | Thanksgiving Break | ||||
Lecture 25 | Nov. 27 | Policy Gradient | [Link] |
[Scribe1]
[Scribe4] |
[Scribe2] | [Scribe3] |
Lecture 26 | Nov. 29 | Review | [Link] | |||
Lecture 27 | Dec. 4 | Project Presentation | [Link] | |||
Lecture 28 | Dec. 6 | Project Presentation | [Link] | |||
Lecture 29 | Dec. 11 | Project Presentation | [Link] | |||
Project Due | Dec. 17 | Project Report Due | ||||
Final Exam | Dec. 19 | Final Exam at 8am to 11am, Room ECEB 1013 & ECEB 1015 |