Grad AI Readings
*** Under development ***
This graduate AI course, CS534, is intended to be a broad introduction to Artificial Intelligence. In addition to the textbook the class will be provided with papers as supplemental reading. These papers are "classic" papers, or good introductions to an area. The readings will be selected from the following (changing) list.
Introduction & Foundations
- Turing, Computing Machinery and Intelligence.
- Newell & Simon, Computer Science as Empirical Enquiry: Symbols and Search.
- Newell & Simon, The theory of human problem solving.
- Searle, Minds, Brains and Programs.
- GAs: Holland, Escaping Brittleness: The possibility of general purpose learning algorithms applied to parallel rule-based systems.
- Mackworth, Consistency in networks of relations.
- Course Notes on Constraint Satisfaction Problems (CSPs)
- Newell, The Knowledge Level
- Minsky, Frames -- A Framework for Representing Knowledge
- Hayes, in defense of logic.
(Hayes, The logic of Frames)
- McCarthy, Concepts of Logical AI
- Davis, Buchanan & Shortliffe, Production Rules as a Representation for a Knowledge-Based Consultation Program.
- an intro to MYCIN
Backtracking & Truth Maintenance
- Doyle, A truth maintenance system.
KB Systems & Architectures
- Nii, Blackboard Systems.
- Shortliffe, Consultation system for physicians.
- Kolodner, Improving human decision making through case-based aiding.
- Buchanan et al (expert systems)
- Winograd, A Procedural Model of Language Understanding
- Schank & Abelson, Scripts, Plans, Goals and Understanding.
- Cohen & Perrault, Elements of a plan-based theory of speech acts.
- Brooks, ACRONYM
- Marr & Poggio, A computational theory of human stereo vision.
- Brooks, Intelligence without representation.
- Fikes & Nillson, STRIPS.
Fikes, Hart & Nillson, Learning & Executing Generaized Robot Plans.
- Stefik, Planning & Meta-planning.
- D.S. Weld (1994). An Introduction to Least-Commitment Planning, AI Magazine, 15(4):27-61.
- Quinlan. Induction of Decision Trees. Machine Learning 1:81-106. 1986.
- Carbonell, Paradigms for Machine Learning
- Winston, Learning structural descriptions from examples.
- Rumelhart, Hinton & Williams, Learning internal representations by error propagation.
- Mitchell, Generalization as search.
Sources of Papers
- Luger, Computation & Intelligence: Collected Readings.
- Readings in AI
- Readings in Cognitive Science
- Readings in Planning
- Readings in Knowledge Representation
- GaTech Intelligent Systems: Areas, Courses, and Readings
- MIT Course Number 6.824: Artificial Intelligence
Mon May 4 22:03:50 EDT 1998