🚀 go-pugleaf

NEW FALL 2001 COURSE OFFERING

Machine Learning
CSCI 4830-007	
Professor Mozer
Tu, Th 9:30-10:45
ECCR 137
call # 14826	

Since the invention of computers, scientists have tried to build computer
systems that learn from experience and adapt to their environments. A machine
learning system does not have to be programmed by humans to solve problems;
instead, it essentially programs itself based on examples of how it should
behave or on trial-and-error experience. Learning algorithms specify how the
system should change its behavior. Researchers in machine learning develop new
learning algorithms, and determine 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
cognitive neuroscience. In the past 15 years, many of these approaches have
converged and led to rapid theoretical advances as well as real-world
applications.

The course focus on methods that have proven valuable and successful in
practical applications (e.g., neural networks, decision trees, Gaussian
processes, support-vector machines, reinforcement learning). Junior standing
is required, as well as one or more of the following courses: statistics, 
probability theory, linear algebra, operations research.