|
|
|
|
Course descriptionThe course introduces the elements of information theory and illustrate their relevance in AI, especially machine learning and pattern recognition. We will also review the mathematical concepts which will be used in the subsequent part of the course. This includes in particular the elements of probability theory, linear algebra, and optimization.PrerequisitesA good background in university-level mathematics (calculus, basic probability, linear algebra).GradingThe course has the following assessment components: 1) Written Examination (2.5 hours, 80%) , 2) Coursework Section (4 pieces, 20%). To pass this course, students must obtain at least 40% on the coursework component and an average of at least 50% when the coursework and exam components of a course are weighted together.Recommended Books and Readings
Information
Theory, Inference & Learning Algorithms
Feynman Lectures on Computation
The Elements of Statistical Learning Additional Reading Material (not necessarily on the course's main topics)
Investigations
(various works by Jim Crutchfield) Other papers:Adaptive Clustering: Better Representatives with Reinforcement Learning
Reinforcement Learning: An Introduction Some students may be interested in my publications, a list I keep of vaguely AI-related books I like, or a list I keep on books related to natural inspired computation.
|
|
Send mail to
robert.elliott.smith@gmail.com with questions or comments about this web
site.
|
