Download Introduction to Artificial Intelligence - Software Practice | CS 3500 and more Assignments Computer Science in PDF only on Docsity! CS 5300: Introduction to AISlide 1 Hal Daumé III (hal@cs.utah.edu) Introduction to AI CS 5300 / CS 6300 Artificial Intelligence Spring 2009 Hal Daumé III hal@cs.utah.edu www.cs.utah.edu/~hal/courses/2009S_AI CS 5300: Introduction to AISlide 3 Hal Daumé III (hal@cs.utah.edu) Course Details Book: Russell and Norvig, AI: A Modern Approach Second Edition (the green one) Prerequisites: CS 3500: There will be a lot of programming CS 2000: There will be a lot of probability Work and grading: Ten short written assignments (10% of grade) May work in groups, but must write-up alone Graded pass/fail, no late submissions Five programming projects (35% of grade) Must work in groups of two or three Late < 2 days at 50% penalty, may be late only twice Midterm (20%) and Final (35%) CS 5300: Introduction to AISlide 4 Hal Daumé III (hal@cs.utah.edu) Announcements Very important stuff: HW0 due Thursday! P0 (Python tutorial) due next Tuesday! Subscribe to mailing list/RSS feed now! Python lab Friday (1pm-4pm) in CADE lab Scott or I will be there the entire time Class is full... If you're going to drop, please drop soon If you need a spot, please wait for someone to drop Questions? CS 5300: Introduction to AISlide 5 Hal Daumé III (hal@cs.utah.edu) Our “sister” course Berkeley, CS 188 taught by John DeNero: http://inst.eecs.berkeley.edu/~cs188/sp09/information.html Thanks to John and Dan Klein for sharing all their work! Courses are ~90% identical Both culminate roughly simultaneously in a Pacman “capture the flag” competition We will run cross-university Pacman servers They've run a similar course for ~3 years Their class is about 2x as big Special prizes for anyone who beats Berkeley! (CTF demo) CS 5300: Introduction to AISlide 6 Hal Daumé III (hal@cs.utah.edu) Today What is AI? Brief history of AI What can AI do? What is this course? CS 5300: Introduction to AISlide 7 Hal Daumé III (hal@cs.utah.edu) Sci-Fi AI? CS 5300: Introduction to AISlide 8 Hal Daumé III (hal@cs.utah.edu) What is AI? Think like humans Think rationally Act like humans Act rationally The science of making machines that: CS 5300: Introduction to AISlide 9 Hal Daumé III (hal@cs.utah.edu) Acting Like Humans? Turing (1950) “Computing machinery and intelligence” “Can machines think?” → “Can machines behave intelligently?” Operational test for intelligent behavior: the Imitation Game Predicted by 2000, a 30% chance of fooling a lay person for 5 minutes Anticipated all major arguments against AI in following 50 years Suggested major components of AI: knowledge, reasoning, language understanding, learning Problem: Turing test is not reproducible or amenable to mathematical analysis CS 5300: Introduction to AISlide 10 Hal Daumé III (hal@cs.utah.edu) Thinking Like Humans? The cognitive science approach: 1960s ``cognitive revolution'': information-processing psychology replaced prevailing orthodoxy of behaviorism Scientific theories of internal activities of the brain What level of abstraction? “Knowledge'' or “circuits”? Cognitive science: Predicting and testing behavior of human subjects (top-down) Cognitive neuroscience: Direct identification from neurological data (bottom-up) Both approaches now distinct from AI Both share with AI the following characteristic: The available theories do not explain (or engender) anything resembling human-level general intelligence Hence, all three fields share one principal direction! Images from Oxford fMRI center CS 5300: Introduction to AISlide 12 Hal Daumé III (hal@cs.utah.edu) Acting Rationally Rational behavior: doing the “right thing” The right thing: that which is expected to maximize goal achievement, given the available information Doesn't necessarily involve thinking, e.g., blinking Thinking can be in the service of rational action Entirely dependent on goals! Irrational insane, irrationality is sub-optimal action≠ Rational successful≠ Our focus here: rational agents Systems which make the best possible decisions given goals, evidence, and constraints In the real world, usually lots of uncertainty … and lots of complexity Usually, we’re just approximating rationality “Computational rationality” a better title for this course