CS 188: Artificial Intelligence Fall 2009Course InformationCourse StaffSlide 4TodaySci-Fi AI?What is AI?Rational DecisionsSlide 9What About the Brain?A (Short) History of AIWhat Can AI Do?Unintentionally Funny StoriesNatural LanguageVision (Perception)RoboticsLogicGame PlayingDecision MakingDesigning Rational AgentsPacman as an AgentReflex AgentsCourse TopicsAnnouncementsSlide 25CS 188: Artificial IntelligenceFall 2009Lecture 1: Introduction8/27/2009Dan Klein – UC BerkeleyMultiple slides over the course adapted fromeither Stuart Russell or Andrew MooreCourse InformationCommunication:Announcements on webpageQuestions? Try the newsgroup!Staff email: [email protected]://inst.cs.berkeley.edu/~cs188Course StaffCourse StaffAditi MuralidharanDan KleinGSIsProfessorDan GillickJeremy Maitin-ShepardDavid BurkettCourse InformationBook: Russell & Norvig, AI: A Modern Approach, 2nd Ed.Prerequisites:(CS 61A or B) and (Math 55 or CS 70) There will be a lot of math and programmingWork and Grading:5 programming projects: Python, groups of 1-25 late days, 2 per project4 written projects: solve together, write-up aloneMidterm and finalParticipationFixed scaleAcademic integrity policyContests!TodayWhat is artificial intelligence?What can AI do?What is this course?Sci-Fi AI?What is AI?Think like humans Think rationallyAct like humans Act rationallyThe science of making machines that:Rational Decisions We’ll use the term rational in a particular way: Rational: maximally achieving pre-defined goals Rational only concerns what decisions are made (not the thought process behind them) Goals are expressed in terms of the utility of outcomes Being rational means maximizing your expected utilityA better title for this course would be:Computational RationalityMaximize Your Expected UtilityWhat About the Brain?Brains (human minds) are very good at making rational decisions (but not perfect)“Brains are to intelligence as wings are to flight”Brains aren’t as modular as softwareLessons learned: prediction and simulation are key to decision makingA (Short) History of AI1940-1950: Early days1943: McCulloch & Pitts: Boolean circuit model of brain1950: Turing's “Computing Machinery and Intelligence”1950—70: Excitement: Look, Ma, no hands!1950s: Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine1956: Dartmouth meeting: “Artificial Intelligence” adopted1965: Robinson's complete algorithm for logical reasoning1970—88: Knowledge-based approaches1969—79: Early development of knowledge-based systems1980—88: Expert systems industry booms1988—93: Expert systems industry busts: “AI Winter”1988—: Statistical approachesResurgence of probability, focus on uncertaintyGeneral increase in technical depthAgents and learning systems… “AI Spring”?2000—: Where are we now?What Can AI Do?Quiz: Which of the following can be done at present?Play a decent game of table tennis?Drive safely along a curving mountain road?Drive safely along Telegraph Avenue?Buy a week's worth of groceries on the web?Buy a week's worth of groceries at Berkeley Bowl?Discover and prove a new mathematical theorem?Converse successfully with another person for an hour?Perform a complex surgical operation?Unload a dishwasher and put everything away?Translate spoken Chinese into spoken English in real time?Write an intentionally funny story?Unintentionally Funny StoriesOne day Joe Bear was hungry. He asked his friend Irving Bird where some honey was. Irving told him there was a beehive in the oak tree. Joe walked to the oak tree. He ate the beehive. The End.Henry Squirrel was thirsty. He walked over to the river bank where his good friend Bill Bird was sitting. Henry slipped and fell in the river. Gravity drowned. The End.Once upon a time there was a dishonest fox and a vain crow. One day the crow was sitting in his tree, holding a piece of cheese in his mouth. He noticed that he was holding the piece of cheese. He became hungry, and swallowed the cheese. The fox walked over to the crow. The End.[Shank, Tale-Spin System, 1984]Natural LanguageSpeech technologiesAutomatic speech recognition (ASR)Text-to-speech synthesis (TTS)Dialog systemsLanguage processing technologiesMachine translationInformation extractionInformation retrieval, question answeringText classification, spam filtering, etc…[demos: language]Vision (Perception)Image from Erik Sudderth•Object and character recognition•Scene segmentation•Image classificaiton[videos: vision]RoboticsRoboticsPart mech. eng.Part AIReality muchharder thansimulations!TechnologiesVehiclesRescueSoccer!Lots of automation…In this class:We ignore mechanical aspectsMethods for planningMethods for controlImages from stanfordracing.org, CMU RoboCup, Honda ASIMO sites[videos: robotics]LogicLogical systemsTheorem proversNASA fault diagnosisQuestion answeringMethods:Deduction systemsConstraint satisfactionSatisfiability solvers (huge advances here!)Image from Bart SelmanGame PlayingMay, '97: Deep Blue vs. KasparovFirst match won against world-champion“Intelligent creative” play200 million board positions per second!Humans understood 99.9 of Deep Blue's movesCan do about the same now with a big PC clusterOpen question:How does human cognition deal with thesearch space explosion of chess?Or: how can humans compete with computersat all??1996: Kasparov Beats Deep Blue“I could feel --- I could smell --- a new kind of intelligence across the table.”1997: Deep Blue Beats Kasparov“Deep Blue hasn't proven anything.”Text from Bart Selman, image from IBM’s Deep Blue pagesDecision Making•Scheduling, e.g. airline routing, military•Route planning, e.g. mapquest•Medical diagnosis•Automated help desks•Fraud detection•Spam classifiers•Web search engines•… Lots more!Designing Rational AgentsAn agent is an entity that perceives and acts.A rational agent selects actions that maximize its utility function. Characteristics of the percepts, environment, and action space dictate techniques for selecting rational actions.This course is about:General AI techniques for a
View Full Document