Spring 2001 Course Offering
CSCI 5622, Section 001
Professor Michael C. Mozer
The goal of machine learning research is to build computer systems that learn from experience and that adapt to their environments. Machine learning systems do not have to be programmed by humans to solve a problem; instead, they essentially program themselves based on examples of how they should behave, or based on trial-and-error experience trying to solve the problem. Machine learning systems require learning algorithms that specify how the system should change its behavior as a result of experience. Researchers in machine learning develop new learning algorithms, and try to understand which algorithms should be applied in which circumstances.
Machine learning is an exciting interdisciplinary field. Its historical roots are in theoretical computer science, statistics, pattern recognition, and even neuroscience. In the past 15 years, many of these approaches have converged and led to rapid theoretical advances as well as real-world applications.
This course will focus on the methods that have proven valuable and successful in practical applications. The course will also contrast the various methods, with the aim of explaining the situations in which each is most appropriate.