Prerequisites: CS 580
Instructor: Prof. Harry Wechsler firstname.lastname@example.org
Course Description: Course covers concepts and techniques in artificial intelligence (AI) for multidisciplinary applications. Topics include basics in probability, statistics, information theory; model selection, complexity, and prediction; learning, training and cross-validation strategies; neural networks and pattern recognition; uncertain knowledge and reasoning; statistical learning, support vector machines (SVM), semi-supervised learning, transduction, collective learning and stochastic relaxation, and anomaly / outlier detection; adversarial learning; ensemble and voting methods; comparative performance evaluation; natural language processing (NLP) using probabilistic learning [Hidden Markov Models (HMM), probabilistic Latent Semantic Analysis (pLSA), and Latent Dirichlet Allocation (LDA)] for text (“document”) retrieval, security applications (“spam and phishing detection”), image analysis (“object localization and recognition”), and biometrics (“face”); emerging themes and future challenges (lack of annotation, uncontrolled settings, interoperability, privacy). (Team) Term project required.
Time, Day, and Venue: M – Monday, 7:20 – 10:00 pm,
Art and Design Building 2026
Office Hours: M – Monday, 6:00 – 7:00 pm, ENGR 4448
First day of classes: Monday, January 27
Spring Break [March 10 – 16]: no class on Monday, March 10
Last day of classes: Monday, May 5
Textbook: Artificial Intelligence by Russell and Norvig, 3rd ed., Prentice Hall, 2010.
Textbook Website (and slides) (for reference): aima.cs.berkeley.edu
· Homework – 30%
· Mid Term – Monday, March 3 – 30 %
· (Team) Project – Class (Slide) Presentation and Final Report, April 28 & May 5 – 40%
You are expected to abide by the GMU honor code. Homework assignments and exams are individual efforts. Information on the university honor code can be found at
Additional departmental CS information: http://cs.gmu.edu/wiki/pmwiki.php/HonorCode/CSHonorCodePolicies