|
Schedule: TU 9-10:20 AM
Building: 61 Room: 106G
Text Books:
Machine Learning: A Probabilistic Perspective by Kevin P. Murphy (Main Book)
Pattern Classification by David G. Stork, Peter E. Hart, and Richard O. Duda
Other Useful Resources:
Pattern Recognition and Machine Learning by Christopher Bishop
Pattern Recognition by Sergios Theodoridis
Artificial Intelligence: A Modern Approach by Peter Norvig and Stuart J. Russell
Probabilistic Graphical Models: Principles and Techniques by Daphne Koller and Nir Friedman
Course Description:
Pattern recognition techniques aim to build an automated system that learns from patterns to make decisions with regards to categories. This course introduces the theory, principles, and practice of statistical pattern recognition from a variety of perspectives. Topics including: supervised (discriminative vs. generative models, parametric vs. non-parametric models, kernel methods, neural network, etc.), unsupervised (e.g., k-means clustering), and semi-supervised learning models (e.g., label propagation) will be presented
Prerequisite:
Students must have graduate standing in computer science or computer engineering. In particular, they should be familiar with linear algebra, probability, and statistics (e.g., CS461 or an equivalent course). The students also should have programming experience in one of the following programming languages: MATLAB/Python/Java/C/C
Course Objectives:
Upon completion of the course, students will be able to formulate machine learning problems corresponding to different real-world applications, apply an appropriate machine learning method to solve a problem of moderate complexity, read and critique research articles in the pattern recognition and machine learning research area, understand and present current research studies in the field, and propose a solution to a machine learning problem and write a research article
Course Outline:
| Topic |
Week |
Introduction to Pattern Recognition and Machine Learning
|
1 |
| Probability Theory -review |
1 |
| Probability Distributions -review |
1 |
| Supervised Learning Models |
2 |
| Parametric vs. Non-parametric Learning Models |
2 |
| Liner Predictions |
2 |
| Kernel Methods |
3 |
| Dimensionality Reduction |
3 |
| Support Vector Machine |
3 |
| Perceptron and Neural Network |
4 |
| Deep Neural Network |
4 |
| Unsupervised Learning Models |
5 |
| Clustering |
5 |
| Semi-supervised Learning Algorithms |
6 |
| Feature Selection and Sampling Methods |
7 |
| Paper Reading and Critiquing |
8-12 |
| Project Presentations |
12-14 |
Paper Reading:
Each student should present two papers at least from the following proceedings
AAAI 15 - AAAI 16- AAAI 17
NIPS 2017- NIPS 2016 - NIPS 2015
|