Artificial Intelligence 人工智能.ppt

Artificial Intelligence人工智能,Xiu-jun GONG(Ph.D)School of Computer Science and Technology,Tianjin U http:/,About the instructor,Name:Xiu-jun GONG(宫秀军)Work experiences2006/05-Now：Associate Professor,Tianjin University2003/05-2006/03:Research fellow,Nara Institute of Science and Technology2003/02-2003/05:Visiting fellow,Institute for Inforcomm Research（I2R),Singapore2002/07-2002/12:Research fellow,National University of Singapore 1999/09-2002/07:Ph.D candidate,Institute of Computing,CASResearch interestsData mining:algorithms,standards,and systemsBioinformatics:gene regulatory network,SNP identificationsMedical informatics:secure,privacy-preserving data mining,medical data integration and sharing framework,About the course,Text bookArtificial Intelligence-A New Synthesis,Nils J.Nillson Artificial Intelligence:A Modern Approach,Stuart Russell and Peter Norvig Artificial Intelligence:Structures and Strategies for Complex Problems Solving(Fourth Edition),George F.Luger GradingAttendance:10%Project&Assignment:20%Final exam:70%Office hour:any time upon pre-appointment before final exam,25-B-1208Web site:http:/,Outline to the introduction,AI definitionsAI historyAI research ProblemsApproachesToolsAI ApplicationsAI resources,What is AI,To make computers think.machines with minds(Haugeland,1985),The study of the computations that make it possible to perceive,reason(Winston,1992),Machines that perform functions that require intelligence when performed by people(Kurzweil,1990),The automation of intelligent behavior(Luger,1993),Thinking humanly Thinking rationally Acting humanly Acting rationally,What is AI(cont.),AI is a branch of cs that is concerned with the automation of intelligent behaviorLugerData structures,algorithms,and language and programming techniques.What is the“intelligent behavior”?Think(act)humanly Think(act)rationally Can machines think?Can:Now or someday;theoretically or actuallyMachine:biological body(made of proteins),mechanical device?Think:media?Living cells or physical symbolic systems,Some synonyms,Intelligent machine,intelligent system,intelligent agent,computational intelligence,synthetic intelligence,Performed by google trends on 7th,Oct,2008,Beyond the definitions,The definitions differ for different people,different contexts,and different historical periods(see the AI history)AI has always been more concerned with expanding the capacities of computer science than with defining its limitsAI is the interdisciplinary study of computer science including psychology,philosophy,neuroscience,cognitive science,linguistics,ontology,operations research,economics,control theory,probability,optimization and logic.,Collection of problems and methodologies studied by AI researchers,History of AI research,Precursors 19431956:The birth of AI 19561974:The golden years19741980:The first AI winter19801987:Boom19871993:Bust:the second AI winter1993present:AI?,Precursors(1),AI in myth,fiction and speculation,Precursors(2),Al-Jazaris programmable automata,Automatons,Formal reasoning,Computer science,19431956:The birth of AI(2),Turings test(1950)-ACT HumanlyDecide whether a machine is intelligent or not,If a machine could carry on a conversation(over a teletype)that was indistinguishable from a conversation with a human being,then the machine could be called intelligent.,19431956:The birth of AI(2),Dartmouth Summer Research Conference on Artificial Intelligence in 1956Marvin Minsky,John McCarthy Coined the term“AI”Every aspect of learning or any other feature of intelligence can be so precisely described that a machine can be made to simulate it-a clear statement of the philosophical position of AI research Presentation of game playing programs and Logic Theorist.,19561974:The golden years(1),Reasoning as search Maze problem-backtrackingCombinatorial explosion-heuristics or rules of thumb“ProjectsSimon etc,General Problem Solver(1951)Herbert Gelernter,Geometry Theorem Prover(1958)James Slagle,SAINT(Symbolic Automatic Integrator)(1961)Nils Nilsson,STRIPS(Stanford Research Institute Problem Solver)(1971),19561974:The golden years(2),Natural language Allow computers to communicate in natural languages-semantic networkSTUDENT,solve high school algebra word problems(1964)ELIZA,rephrasing many of the patients statements as questions and posing them to the patients(1966)ALICE:http:/www.alicebot.orgMicro-worlds Marvin Minsky,machine visionThey pointed out that in successful sciences were often best understood using simplified models like frictionless planes or perfectly rigid bodies.Much of the research focused on the so-called blocks world,which consists of colored blocks of various shapes and sizes arrayed on a flat surface.,19741980:The first AI winter(1),Critiques from across campus(mainly from philosophers)John Lucas,argued Gdels incompleteness theorem(a formal system could never see the truth of certain statements,while a human being could)Hubert Dreyfus,argued that human reasoning actually involved very little symbol processing and a great deal of embodied,instinctive,unconscious know how.John Searle,Chinese Room argument(a program could not be said to understand the symbols that it uses)Perceptrons and the dark age of connectionismperceptron may eventually be able to learn,make decisions,and translate languages(Frank Rosenblatt,1958)Minsky and Paperts,book Perceptrons.1969,19741980:The first AI winter(2),The neats:logic,Prolog and expert systemsLogic into AI:McCathy 1958Deduction on computers:J.Alan Robinson 1963Prolog:Philippe Roussel,Alain Colmerauer,1972Critics:human beings rarely used logic when they solved problems The scruffies:frames and scriptsGerald Sussman observed that using precise language to describe essentially imprecise concepts doesnt make them any more precise.Minsky noted that many of his fellow scruffy researchers were using the same kind of tool:a framework that captures all our common sense assumptions about something.1975,19801987:Boom(1),The rise of expert systems(main stream of AI)MYCIN,1972,diagnosed infectious blood diseases XCON(eXpert CONfigurer),1980,automatically selecting the computer system components based on the customers requirements The knowledge revolutionThe power of expert systems came from the expert knowledge they contained Cyc(enCyclopedia),assemble a comprehensive ontology and database of everyday common sense knowledg,Douglas Lenat 1984,19801987:Boom(2),The revival of connectionismJohn Hopfield(associative neural network,1982)David Rumelhart(backpropagation)The money returnsthe fifth generation project($850 million,1982,10-year program)“epoch-making computer”massive parallel processing Failure in 1992Alvey(England,350)(1983-1987)Strategic Computing Initiative(DARPA)(1984),PIM/m-1 machine,19871993:the second AI winter,Market changedDesktop computers from Apple and IBM had been steadily gaining speed and powerRobotics factshaving a body essentiallyA machine needs to have a body it needs to perceive,move,survive and deal with the worldDavid Marr,AI needed to understand the physical machinery of vision from the bottom up before any symbolic processing took place.Rodney Brooks,Elephants Dont Play Chess,symbols are not always necessary since the world is its own best model”.“physical symbol system hypothesis”,1993present:AI?,Deep Blue beats Kasparov(1997)DARPA grand challenge:Autonomous vehicle navigates across desert.(Urban Challenge next)2005NASA Remote Agent in Deep Space I probe explores solar systemiRobot Roomba automated vacuum cleanerAutomated speech/language systems for airline travelUsable machine translation thru Google?,Advanced Intelligence,Close interactions and coordination between Natural Intelligence and Artificial IntelligenceThe frontiers in both Artificial Intelligence and Natural IntelligenceLarge-scale Distributed Intelligence and Web Intelligence,China s Programs on AI,国家中长期科学和技术发展规划纲要（2006-2020）重点领域及其优先主题传感器网络及智能信息处理重点开发多种新型传感器及先进条码自动识别、射频标签、基于多种传感信息的智能化信息处理技术，发展低成本的传感器网络和实时信息处理系统，提供更方便、功能更强大的信息服务平台和环境。基础研究：脑科学与认知科学 主要研究方究向：脑功能的细胞和分子机理，脑重大疾病的发生发展机理，脑发育、可塑性与人类智力的关系，学习记忆和思维等脑高级认知功能的过程及其神经基础，脑信息表达与脑式信息处理系统，人脑与计算机对话等。,Problems of AI,Deduction,reasoning,problem solvingKnowledge representationPlanningLearningNatural language processingMotion and manipulationPerceptionSocial intelligenceCreativityGeneral intelligence,Approaches to AI,Acting rationallyThe rational agent approach,Thinking humanlyThe cognitive approach,Acting humanlyThe Turing Test approach,Thinking rationallyThe laws of thought approach,Approaches to AI cont.,SymbolismCognitive simulation:Psychologism-Herbert Simon and Alan Newell)Logical AI:Logicism-John McCarthy Scruffy symbolic AI:Computerism,commonsense knowledge bases-Marvin MinskyConnectionism Hopfield,PittsNeural networksActionism BrooksCybernetics and brain simulation,Tools of AI research,Search and optimizationLogicProbabilistic methods for uncertain reasoningClassifiers and statistical learning methodsNeural networksControl theory,Specialized languages,Lisp is a practical mathematical notation for computer programs based on lambda calculusProlog is a declarative language where programs are expressed in terms of relations,and execution occurs by running queries over these relationsSTRIPS a language for expressing automated planning problem instances.Planner is a hybrid between procedural and logical languages.,Application domains,Machine LearningNatural Language ProcessingExpert SystemPatten RecognitionComputer VisionRoboticsGame PlayingAutomatic Theorem ProvingAutomatic Programming,机器学习 自然语言处理 专家系统模式识别 计算机视觉 机器人学 博弈 自动定理证明 自动程序设计,Application domains(cont.),Intelligent ControlIntelligent Decision Support SystemArtificial Neural NetworkKnowledge Discovery in Database&Data MiningDistributed AIIntelligent AgentIntelligent Retrieval from Database,智能控制 智能决策支持系统 人工神经网络 知识发现和数据挖掘 分布式人工智能 智能代理智能数据库检索,AI resources:Journals(premium),Artificial IntelligenceComputational LinguisticsIEEE Trans on Pattern Analysis and Machine IntlIEEE Trans on Robotics and AutomationIEEE Trans on Image ProcessingJournal of AI ResearchNeural ComputationMachine LearningIntl Jnl of Computer VisionIEEE Trans on Neural Networks,AI resources:Journals(leading),Artificial Intelligence ReviewACM Transactions on Asian Language Information ProcessingAI MagazineApplied Artificial IntelligenceArtificial Intelligence in MedicineComputational IntelligenceComputer Speech and LanguageExpert Systems with Applications:An Intl Jnl IEEE Trans on Systems,Man,&Cybernetics,Part A&BIntl Jnl on Artificial Intelligence ToolsJnl of Experimental&Theoretical AIJournal of East Asian LinguisticsKnowledge Engineering ReviewMachine TranslationNeural NetworksPattern RecognitionNeurocomputing,AI competitions,Machine Intelligence PrizeLoebner prize KDD Cup serires,AI resources:Conferences,AAAI:American Association for AI National ConferenceCVPR:IEEE Conf on Comp Vision and Pattern RecognitionIJCAI:Intl Joint Conf on AIICCV:Intl Conf on Computer VisionICML:Intl Conf on Machine LearningKDD:Knowledge Discovery and Data MiningKR:Intl Conf on Principles of KR&ReasoningNIPS:Neural Information Processing SystemsUAI:Conference on Uncertainty in AIAAMAS:Intl Conf on Autonomous Agents and Multi-Agent SystemsACL:Annual Meeting of the ACL(Association of Computational Linguistics),Summary,AI definitionWhatever the definition is,Collection of problems and methodologies studied by AI researchers is an important clue for investigating AI problemsAI historyHistory is a mirror.AI researchers are getting more intelligent AI researchIntegration of multi-disciplines.,Bring AI into practice and reality,