CATALOG DESCRIPTION: Core techniques and applications of artificial intelligence. Representation retrieving and application of knowledge for problem solving. Hypothesis exploration, theorem proving, vision and neural networks.
REQUIRED TEXTBOOK : Russell & Norvig , Artificial Intelligence: A Modern Approach , Prentice Hall, 3rd edition
COURSE COORDINATOR: Chris Riesbeck
COURSE GOALS: The goal of this course is to expose students to the basic ideas, challenges, techniques, and problems in artificial intelligence. Topics include strong (knowledge-based) and weak (search-based) methods for problem solving and inference, and alternative models of knowledge and learning, including symbolic, statistical and neural networks.
PREREQUISITES: EECS 325, EECS 111, or Lisp programming experience
DETAILED COURSE TOPICS:
- Philosophical foundations of artificial intelligence
- Intelligent agents
- Search, including A*, iterative deepening
- Logical formalisms, propositional and first order predicate calculus
- Planning, from STRIPS to Partial Order Planning
- Probability & uncertainty, including Bayesian inference and Bayes networks
- Machine learning, including decision trees, neural nets, hill climbing, genetic algorithms
HOMEWORK ASSIGNMENTS: Varies, but always involves at least 3 major programming assignments, plus readings and/or papers.
LABORATORY PROJECTS:
GRADES:
- Homeworks 50%
- Exams 40%
- Participation and extra credit 10%
COURSE OBJECTIVES: After this course, students should be able to
- Articulate key problems, both technical and philosophical, in the development of artificial intelligence
- Teach themselves more about AI through reading texts and research articles in the field
- Apply AI techniques in the development of problem-solving and learning systems
