Artificial-IntelligenceP教学讲解课件.ppt

1、1Artificial IntelligenceCS 165AFall 2004 Lecture 1Prof.Terry Smith Course introduction and overviewCourse administriviaOverview of AI2Goals of this course To teach you the main ideas of AI To introduce you to a set of key techniques and algorithms from AI To help you understand whats hard in AI and

2、why To see how AI relates to the rest of computer science To get you thinking about how AI can be applied to a variety of real problems To have fun3Course administrivia Web sites http:/www.cs.ucsb.edu/cs165a http:/ Syllabus Discussion sessions Schedule AssignmentsAssignment#0 due on Tuesday!Expectat

3、ions Come to class,and come prepared Participate:Ask questions,offer insight,tell me Im wrong.Think!4What is Artificial Intelligence?AI in the media Popular movies2001:A Space Odyssey Star TrekThe TerminatorAI:The Movie Popular press,novels Often portrayed as A property of evil computers Computers d

4、oing impossible things Public view Books and movies have inspired many AI researchers Books and movies have raised the publics expectations5What is Artificial Intelligence?(cont.)“The science and engineering of making intelligent machines,especially intelligent computer programs.”“The business of ge

5、tting computers to do things they cannot already do,or things they can only do in movies and science fiction stories.”“The study of how to make computers do things at which,at the moment,people are better.”“The design of flexible programs that respond productively in situations that were not specifi

6、cally anticipated by the designer.”“The construction of computations that perceive,reason,and act effectively in uncertain environments.”“The branch of CS concerned with enabling computers to simulate such aspects of human intelligence as speech recognition,deduction,inference,creative response,the

7、ability to learn from experience,and the ability to make inferences given incomplete information.”“Modeling aspects of human cognition on computers”“What AI people do”6Goals of AI Scientific To understand the principles and mechanisms that account for intelligent action Engineering To design intelli

8、gent systems that can survive and operate in the real world and solve problems of considerable scientific difficulty at high levels of competenceTo understand and build intelligent systemsTo create models and mechanisms of intelligent action7Intelligent systems An intelligent system is characterized

9、 as one that can:Exhibit adaptive,goal-oriented behavior Learn from experience Use vast amounts of knowledge Exhibit self-awareness Interact with humans using language and speech Tolerate error and ambiguity in communication Respond in real-time8What AI people studyLogicKnowledge representationSearc

10、hReasoning/inferenceNon-monotonic reasoningPlanningProbabilistic reasoningNave physicsMachine learningSpeech recognitionNatural language processingComputer visionPattern recognitionIntelligent agentsRoboticsNeural networksData miningExpert systems and more9What AI people(and programs)doProve theorem

11、sEmulate/model human cognitive abilities(Attempt to)solve exponentially hard problemsBuild expert systems for diagnostic tasks(e.g,medical diagnosis,error analysis)Build robotsBuild machine vision systems for industrial tasks,surveillance,consumer apps,etc.Create speech recognition and understanding

12、 systems for various domainsProcess text to understand,summarize,correct,respond,etc.Create data mining systems to process very large amounts of information(e.g.,bioinformatics)Build intelligent agents to look and act in socially useful waysDevelop computer games and more10Some notable AI systemsIBM

13、s Deep Blue Beat world chess champion Gary Kasparov in 1997 Kasparov vs.(Israeli-built)Deep Junior,January 2003(ended in a draw)Kasparov vs.X3D Fritz,November 2003Expert systems Medical diagnosisA computerized Leukemia diagnosis system did a better job checking for blood disorders than human experts

14、Speech recognition Commercial systems by Dragon,IBM,and others Phone-based systems(e.g.,airline reservations)Automatic scheduling for manufacturing operationsUser interface Grammar and spelling checkers,automated help11Some notable AI systems(cont.)Data mining Fraud detection,credit scoring,customer

15、 profiles and preferences,genome analysisCyc Doug Lenats 18-year old project to give computer common senseComputer vision E.g.,“Hands Across America”1995 Face recognition systems for biometricsRobotics Mars Rover,robots for hazard environments,factory automation Sony,Honda,others:robot pets CMU Navl

16、ab drove across country(2797/2849 miles)1980s DARPA ALV Program DARPA Grand Challenge 2004Failed in 2004repeat in October 200512DARPA Grand Challenge“DARPA intends to conduct a challenge of autonomous ground vehicles between Los Angeles and Las Vegas in March of 2004.A cash award of$1 million will b

17、e granted to the team that fields the first vehicle to complete the designated route within a specified time limit.”http:/www.darpa.mil/grandchallenge13Terrain between LA and Las Vegas14Perspectives on AI/Disciplines involved AI functions as a channel of ideas between computing and other fields,idea

18、s that have profoundly changed those fields Logic Mathematics Statistics Philosophy Psychology Linguistics Neuroscience Computer science Cognitive scienceAI15Foundations of AI Philosophy Framed the ideas of AIDualism/materialism,logical/rational/empirical,causality,consciousness,mind/body Mathematic

19、s Formalized computation,logic,probability Possibilities and limitations of computation Psychology Experimental:the brain as an information processing device(Cognitive Science)Computer Engineering Built real machines,Moores Law progress16AI and Computer Science AI is mostly about software(usually la

20、rge and complex)Important:Algorithms,tools,complexity,etc.Early advanced in CS due to AI researchers include:Search algorithms List structures,pointers Virtual memory Dynamic memory allocation Garbage collection Logical programming CS 165A will be taught primarily from a CS perspective Not the only

21、perspective,though17UCSB CS AI Sequence:165A and 165B165A.Artificial Intelligence(Fall)(4)TURKPrerequisites:Computer Science 130A;open to computer science majors onlyAn introduction to the field of Artificial Intelligence,which attempts to understand and build intelligent systems.Topics include AI p

22、rogramming languages,search,logic,knowledge representation and reasoning,game playing,planning,uncertainty,perception,and intelligent agents.165B.Machine Learning(Winter)(4)SMITH/SUPrerequisites:Computer Science 165AThe course covers the most important techniques of machine learning(ML)and includes

23、discussions of:well-posed learning problems;artificial neural networks;concept learning and general to specific ordering;decision tree learning;genetic algorithms;learning sets of rules;Bayesian learning;analytical learning;and combining inductive and analytical learning.The course integrates these

24、approaches to learning with fundamental aspects of machine intelligence(MI),including search,knowledge representation and reasoning,and applications.18“Proper”backgroundBlind search(depth-first,breadth-first)CS 130ATrees(programming)CS 20,50,130ABoolean logic,Propositional logic,First-order logic CS

25、 40Probability,Bayes rule PSTAT 120AParsing CS 20,160(some)C+/Java several19AI=“A”+“I”Artificial As in“artificial flowers”or“artificial light”?Intelligence What is intelligence?The capacity to acquire and apply knowledgeThe faculty of thought and reasonSecret information,especially about an actual o

26、r potential enemySymbol manipulation,grounded in perception of the worldThe computational part of the ability to achieve goals in the world What makes someone more/less intelligent than another?Are monkeys,ants,trees,babies,chess programs intelligent?How can we know if a machine is intelligent?Turin

27、g Test(Alan Turing,1950),a.k.a.The Imitation Game20Replicating human intelligence?AI doesnt necessarily seek to replicate human intelligence Sometimes more,sometimes less“Essence of X”vs.“X”Examples Physical vs.electronic newspaper Physical vs.virtual shopping Birds vs.planes“Saying Deep Blue doesnt

28、 really think about chess is like saying an airplane doesnt really fly because is doesnt flap its wings.”Drew McDermott21“Strong AI”vs.“Weak AI”“Strong AI”Makes the bold claim that computers can be made to think on a level(at least)equal to humans One version:The Physical Symbol System HypothesisA p

29、hysical symbol system has the necessary and sufficient means for general intelligent actionIntelligence=symbol manipulation(perhaps grounded in perception and action)“Weak AI”Some“thinking-like”features can be added to computers to make them more useful tools Examples:expert systems,speech recogniti

30、on,natural language understanding.22“Strong AI”vs.“Weak AI”(cont.)Principles of“Strong AI”Intelligent behavior is explicable in scientific terms;a rigorous understanding of intelligence is possible Intelligence can take place outside the human skull The computer is the best laboratory instrument for

31、 exploring these propositions Maybe Strong AI is science?Weak AI is engineering?23Philosophical and ethical implications Is“Strong AI”possible?If so(or even if not)Should we be worried?Is this technology a threat?(Bill Joy)Is it okay to kill an intelligent machine?When will it happen?(Will we know?)

32、Will they keep us around?(Kurzweil,Moravec)Might we become too dependent on technology?Terrorism,privacy Main categories of objections to AI Nonsensical(Searle)Impossible(Penrose)Unethical,immoral,dangerous(Weizenbaum)Failed(Wall Street)24Another way of looking at AIThought processes and reasoningBe

33、haviorHumanIdealSystems that think like humansSystems that think rationallySystems that act like humansSystems that act rationally25Human/Biological Intelligence Thinking humanly(Cognitive modeling)Cognitive science1960s Information processing replaced behaviorism as the dominant view in psychology

34、Cognitive neuroscienceNeurophysiological basis of intelligence and behavior?Acting humanly(Operational intelligence)The Turing Test operational test for intelligent behaviorWhat does it require?Required:knowledge,reasoning,language understanding,learning Problem:It is not reproducible or amenable to

35、 mathematical analysis;rather subjective26Ideal/Abstract Intelligence Thinking rationally(Laws of Thought)Rational thought:governed by“Laws of Thought”Logic approach mathematics and philosophy Acting rationally(Rational agents)Rational behavior:doing the right thingMaximize goal achievement,given th

36、e available information(knowledge+perception)Can/should include reflexive behavior,not just thinking General rationality vs.limited rationality Basic definition of agent something that perceives and acts27How can you tell its AI?It does something that is clearly“human-like”or Separation of data/know

37、ledge operations/rules control Has a knowledge representation framework problem-solving and inference methods28Why study AI?Its fascinating Deep questions about intelligence,consciousness,the nature of being human Grand challenges creating intelligent machines Multidisciplinary endeavor It leads to

38、a different perspective on computer science issues Levels of explanation Search,problem solving,etc.higher level approach Exponential,NP-hard problems Its good background for related areas Computer vision,speech recognition,natural language understanding,probabilistic reasoning systems,machine learn

39、ing,etc.29A quoteThe hardest applications and most challenging problems,throughout many years of computer history,have been in artificial intelligence AI has been the most fruitful source of techniques in computer science.It led to many important advances,like data structures and list processing.art

40、ificial intelligence has been a great stimulation.Many of the best paradigms for debugging and for getting software going,all of the symbolic algebra systems that were built,early studies of computer graphics and computer vision,etc.,all had very strong roots in artificial intelligence.Donald Knuth3

41、0Will it get me a job?Well.Not as many AI jobs as Java programming jobs.But See web site(Announcements)for relevant articles AI is a component of many advanced technologies A thorough understanding of the concepts covered in the course will make you a better computer scientist You will have a broade

42、r array of tools with which to approach problems You will better be able to evaluate technologies with AI components AI related research usually requires a graduate degree31A note on AI programming Lisp List processing Interpreter great for fast prototyping Features:garbage collection,dynamic typing

43、,.Prolog Logic programming Program=set of logical statements+general theorem prover Other high-level languages(Java,C+,etc.)32p 经常不断地学习,你就什么都知道。你知道得越多,你就越有力量p Study Constantly,And You Will Know Everything.The More You Know,The More Powerful You Will Be写在最后33谢谢你的到来学习并没有结束，希望大家继续努力Learning Is Not Over.I Hope You Will Continue To Work Hard演讲人：XXXXXX 时 间：XX年XX月XX日