ECE544NA: Pattern Recognition (Fall 2017)
Course Information
ECE 544NA is a special topics course in pattern recognition, and content varies every year. In Fall 2017, the course will cover three main areas, (1) disciminative models, (2) generative models, and (3) reinforcement learning models. 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 the students should be familiar with the underlying theory and software that are frequently used in publications related to pattern recognition.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.
Instructor & TAs
Alexander Schwing
InstructorEmail: aschwing[at]illinois.edu
Office Hour: Tues. 12:30-1:30PM
Room: CSL 103
Website: [link]
Raymond Yeh
Head Teaching AssistantEmail: yeh17[at]illinois.edu
Office Hour: Tues. 12:30-1:30PM
Room: ECEB 4034
Website: [link]
Teck Yian Lim
Teaching AssistantEmail: tlim11[at]illinois.edu
Office Hour: Monday 10:00-11:00AM
Room: ECEB 3034
Website: [link]
Safa Messaoud
Teaching AssistantEmail: messaou2[at]illinois.edu
Office Hour: Friday 4:00-5:00PM
Room: ECEB 4034
Website: [link]
Lectures
Note:This syllabus is subject to change.
| Event | Date | Description | Materials |
|---|---|---|---|
| Lecture 1 | August 29 | Intro to Pattern Recognition | [Slides] |
| Assignment 0 Assigned | August 29 | Assignment 0: Introduction + Python |
[Assignment 0] |
| Assignment 1 Assigned | August 29 | Assignment 1: Binary Classification |
[Assignment 1] |
| Project Assigned | August 29 | Final Project Instructions |
[Project] |
| Topics on Discriminative Models | |||
| Lecture 2 | August 31 | Linear Regression | [Slides] |
| Lecture 3 | September 5 | Logistic Regression | [Slides] |
| TA Lecture | September 7 | Machine Learning Pipeline + TensorFlow Intro (by Raymond) | [Slides] [Ipython] |
| Lecture 4 | September 12 | Optimization Primal | [Slides] |
| Lecture 5 | September 14 | Optimization Dual | [Slides] |
| Assignment 0 Due | September 14 | Assignment 0: Introduction + Python | [Assignment 0] |
| Lecture 6 | September 19 | Support Vector Machines | [Slides] |
| Lecture 7 | September 21 | Multiclass classification and Kernel Methods | [Slides] |
| Assignment 1 Due | September 21 | Assignment 1: Binary Classification | [Assignment 1] |
| Assignment 2 Assigned | September 21 | Assignment 2: Deep Learning and Graphical Models for Image Denoising |
[Assignment 2] |
| Lecture 8 | September 26 | Deep Neural Networks | [Slides] |
| TA Lecture | September 28 | TensorFlow + Google Cloud | [Slides] |
| Project Due | September 28 | Project: Proposal |
[Project] |
| Lecture 9 | October 3 | Structured Prediction (exhaustive search, dynamic programming) | [Slides] |
| Lecture 10 | October 5 | Structured Prediction (ILP, LP relaxation, message passing, graph cut) | [Slides] |
| Lecture 11 | October 12 | Conditional Random Fields and Structured SVMs (learning) | [Slides] |
| Lecture 12 | October 17 | Deep Structured Methods (inference and learning) | [Slides] |
| Assignment 2 Due | October 19 | Assignment 2: Deep Learning and Graphical Models for Image Denoising | [Assignment 2] |
| Assignment 3 Assigned | October 19 | Assignment 3: Generative Models |
[Assignment 3] |
| Topics on Generative Models | |||
| Lecture 13 | October 19 | K-Means | [Slides] |
| Lecture 14 | October 24 | Gaussian Mixture Models | [Slides] |
| Lecture 15 | October 26 | Expectation maximization/Majorize-Minimize/Concave-convex procedure | [Slides] |
| Lecture 16 | October 31 | Structured Latent Variable Models (e.g., HMMs) | [Slides] |
| Lecture 17 | November 2 | Variational Auto-encoders | [Slides] |
| Lecture 18 | November 7 | Generative Adversarial Nets | [Slides] |
| Lecture 19 | November 9 | Autoregressive Methods | [Slides] |
| Assignment 3 Due | November 9 | Assignment 3: Generative Models | [Assignment 3] |
| Assignment 4 Assigned | November 9 | Assignment 4: Reinforcement Learning |
[Assignment 4] |
| Topics on Reinforcement Learning Models | |||
| Lecture 20 | November 14 | Markov Decision Processes | [Slides] |
| Lecture 21 | November 16 | Q-learning | [Slides] |
| No Lecture | November 21 | Thanksgiving Break | [Slides] |
| No Lecture | November 24 | Thanksgiving Break | [Slides] |
| Lecture 22 | November 28 | Policy Gradient | [Slides] |
| Lecture 23 | November 30 | Actor-Critic | [Slides] |
| Assignment 4 Due | November 30 | Assignment 4: Reinforcement Learning | [Assignment 4] |
| Lecture 24 | December 5 | Final Exam Review | [Slides] |
| Lecture 25 | December 7 | Final Project Presentations | [Slides] |
| Lecture 36 | December 12 | Final Project Presentations | [Slides] |
| Project Due | Dec. 18 | Project: Written Report + Code |
[Project] |
| Final Exam | Dec. 18 | Room: ECEB 2015 and ECEB 2017 | [Slides] |