Principles of Artificial Intelligence. ComS 572 (472 DL).

3 Credits. Offered every fall. Prerequisites: Com S 208 or 228, ComS 330 or CprE 310.

Instructor: Vasant Honavar

Overview - foundations, scope, and problems of artificial intelligence and cognitive science. State-space search techniques for problem solving. Knowledge representation and automated inference. Machine learning. Introduction to neural and evolutionary approaches to AI. Selected applications in planning, machine perception, analysis, design. AI programming using Common LISP. Graduate credit requires a research project and a written report.

Elements of Neural Computation. ComS 474.

3 Credits. Offered every spring. Prerequisites: Math 165, ComS 212 or 208 or 228.

Instructor: Vasant Honavar

Introduction to mathematical and computational models of neurons and networks of neurons. Associative memory, pattern classification, function approximation properties of neural networks. Covers a range of network models and learning algorithms and their applications in Artificial Intelligence, Cognitive and Neural Modeling and Computer Science. Hands-on experience with neural computing is emphasized through the use of simulation tools and programming projects.

Computational Models of Learning. ComS 672.

3 Credits. Offered Alternate Spring. Next Scheduled Offering 1997. Prerequisites: ComS 572 or 472 or 474.

Instructor: Vasant Honavar

Advanced study of Artificial Intelligence, Statistical, Neural, Syntactic, Evolutionary models and algorithms for machine learning. Inductive learning, classification, grammar induction, function approximation, program induction (inductive logic programming). Deductive learning. Discovery. Elements of computational learning theory. Selected Applications.

Advanced Topics in Artificial Intelligence and Cognitive Modeling. ComS 673.

3 Credits. Offered Alternate Spring. Next Scheduled Offering 1998. Prerequisites: ComS 572 or 472 or 474.

Instructor: Vasant Honavar

Advanced study of topics in AI and cognitive modelling slected from among the following: Parallel and distributed architectures and algorithms for artificial intelligence; Computational Models of Discovery; Machine learning; Neural networks and Neural Modeling; Genetic algorithms, Genetic programming and Artificial Life. Computational Learning Theory. Evolutionary Robotics. Intelligent Agent Architectures. Selected applications of AI. Click here for more information about spring 1996 offering of this course.

Artificial Intelligence Research Seminar. ComS 610.

1-3 Credits. Generally offered every term.

Instructor: Vasant honavar

Topics vary from term to term. Recent offerings have focused on current research in Genetic Algorithms, Genetic Programming, Artificial Life, Intelligent Agent Architectures, Neural Networks, Hybrid Intelligent Systems, Machine Learning, Computational Learning Theory, Inductive Logic Programming, Language Learning, Parallel Architectures and Algorithms for Artificial Intelligence, Applications in Communications Network Management, Scientific Discovery, VLSI design, Parallel and Distributed Computing, and Cognitive and Neural Modeling. Click here for information about the current offering.

Directed Independent Study (Computer Science)

Directed independent study and research can be accomodated at both undergraduate as well as graduate levels. Interested undergraduates should look into ComS 290, ComS 290H, ComS 490 and ComS 490H and graduate students should consider ComS 590, ComS 599, and ComS 699.

Optimization and Modeling with Artificial Life Math 378X

3 Credits. Next Scheduled Offering 1995. Prerequisites: Discrete math (one of math 301, 304, 330) and programming experience.

Instructor: Daniel Ashlock