Revised October 17, 2011
CS 485: Machine Learning
Watch a video introduction to this course on YouTube.
General Description
Machine learning is a fast growing topic for both commercial applications and academic research. It addresses the issue of how computers can "learn", that is, how the process of drawing useful conclusions from massive data sets can be automated. Machine learning plays a central role in a wide range of applications emerging from the need to process data sets whose sizes and complexities are beyond the ability of humans to handle. The course will cover the theoretical foundations and the design of algorithms for machine learning. It draws from several established mathematical areas including statistics, geometry, combinatorics, and computational complexity.
Logistics
CS 485 is a course for Computer Science, Software Engineering and Math major students, and is normally completed in a student's fourth year. The course should be relevant for all students who are interested in computational statistics, data mining, information retrieval, artificial intelligence, natural language processing, computer vision, computation finance, bioinformatics and health informatics where it is common to analyze massive data sets or it is desirable to design adaptive algorithms.
Related courses (see calendar for official details)
- Predecessors: CS 341 and (STAT 206 or 230 or 240).
Typical Reference(s)
Christopher Bishop, Pattern Recognition and Machine Learning (2006) Shai Ben-David & Shai Shalev-Shwartz, Machine Learning: From Theoretical Principles to Practical Algorithms (in preparation)
Typical syllabus
Introduction to machine learningTheoretical foundation
e.g. learning theory and Bayesian learning
ClassificationRegression
Dimensionality reduction
Specific models/algorithms
e.g., naive Bayes, decision trees, neural networks, kernel methods, support vector machines, ensemble learning