《人工智能详解课件.ppt》由会员分享，可在线阅读，更多相关《人工智能详解课件.ppt（69页珍藏版）》请在三一办公上搜索。
1、Modern Artificial Intelligence and Its Importance in the Future World,Zengchang Qin (Ph.D.)Intelligent Computing and Machine Learning LabSchool of Automation and Electrical EngineeringBeihang UniversityShahe Campus Oct 27 2010,This is Science,Give a big picture of modern Artificial Intelligence and
2、understand why it is important in the current and the future world.We have such a direction of research in the school of ASEE. To clarify the misunderstanding of A.I. from those robot movies and science fictions.,About This Talk,I have been working in A.I. are for the past decade. I enjoy movies and
3、 unbounded thinking.I am always intrigued by any kinds f excellent ideas from human intelligence. Feel free to ask any questions you have in mind, no guarantee to be answered.,About The Speaker,Misunderstanding,Artificial Intelligence (A.I.) RoboticsJohn McCarthy (Stanford),Artificial Intelligence W
4、e fear?,I, Robot,The Three Laws of Robotics by Issac Asimov are as the follows:A robot may not injure a human being or, through inaction, allow a human being to come to harm. A robot must obey any orders given to it by human beings, except where such orders would conflict with the First Law. A robot
5、 must protect its own existence as long as such protection does not conflict with the First or Second Law.,My Philosophy of Modern A.I.,Artificial Intelligence is a mathematical/computing technology that will make life better. I have been interested in making machines intelligent by designing algori
6、thms. I may not believe that one day we can recreate human brains using silicon chips, but I believe that computing will aid our brains to do missions impossible in the future.,Chinese Room Paradox,Modern A.I. The Engineering Approach: Machine Learning and Data Mining,Pattern Recognition, Computer v
7、ision and Image ProcessingDistributed A.I. /multi-agent systemsBiometrics and computer forensicsNatural Language ProcessingIntelligent Search and Information RetrievalComputational Cognitive ScienceComputational Neuroscience and bioinformaticsComputational Cognitive ScienceComputational/Behavior Fin
8、anceBehavior Targeting and Personal ServicesDigital Advertisements/recommendation systems,Philosophy of Machine Learning,Machine Learning search in the hypothesis space to find the ones that match the data. Using Occams razor, we choose the simplest one.William of Ockham (or Occam) was a 14th-centur
9、y English logician and Franciscan friar whos name is given to the principle that when trying to choose between multiple competing theories the simplest theory is probably the best. This principle is known as Ockhams razor.,Example,Example 2,Why Machine Learning is important?,To fine the theory that
10、explains the data, we usually prefer the simple ones. Machine learning and scientific discovery share similarities. Karl Popper,Logic Programming,London Underground Example,Fuzzy Logic,Membership function (continuous),Membership Functions,Some Intuition,Professor of Fuzzy Logic,Multi-agent System,Di
11、stributed A.I. - coordination,Data miningis the process of extracting patterns from data - Torture the data until they confess.Data is everywhere and in different types.,Pattern Recognition and Data Mining,Welcome to FairmontNET.stdtext font-family: Verdana, Arial, Helvetica, sans-serif; font-size:
12、11px; color: #1F3D4E;.stdtext_wh font-family: Verdana, Arial, Helvetica, sans-serif; font-size: 11px; color: WHITE; ,HTML and Emails,Return-path Receivedfrom relay2.EECS.Berkeley.EDU (relay2.EECS.Berkeley.EDU 169.229.60.28) by imap4.CS.Berkeley.EDU (iPlanet Messaging Server 5.2 HotFix 1.16 (built Ma
13、y 14 2003) with ESMTP id ; Tue, 08 Jun 2004 11:40:43 -0700 (PDT)Receivedfrom relay3.EECS.Berkeley.EDU (localhost 127.0.0.1) by relay2.EECS.Berkeley.EDU (8.12.10/8.9.3) with ESMTP id i58Ieg3N000927; Tue, 08 Jun 2004 11:40:43 -0700 (PDT)Receivedfrom redbirds (dhcp-168-35.EECS.Berkeley.EDU 128.32.168.3
14、5) by relay3.EECS.Berkeley.EDU (8.12.10/8.9.3) with ESMTP id i58IegFp007613; Tue, 08 Jun 2004 11:40:42 -0700 (PDT)DateTue, 08 Jun 2004 11:40:42 -0700FromRobert Miller SubjectRE: SLT headcount = 25In-reply-toToRandy Katz CcGlenda J. Smith , Gert Lanckriet Message-idMIME-version1.0X-MIMEOLEProduced By
15、 Microsoft MimeOLE V6.00.2800.1409X-MailerMicrosoft Office Outlook, Build 11.0.5510Content-typemultipart/alternative; boundary=-=_NextPart_000_0033_01C44D4D.6DD93AF0Thread-indexAcRMtQRp+R26lVFaRiuz4BfImikTRAA0wf3Qthe headcount is now 32. - Robert Miller, Administrative Specialist University of Calif
16、ornia, Berkeley Electronics Research Lab 634 Soda Hall #1776 Berkeley, CA 94720-1776 Phone: 510-642-6037 fax: 510-643-1289,24,Medical Image, handwritten recognition,25,Sounds - fingerprints,26,Intelligent Search and Bio-identity,Mirco-array Data of Genes,Drug Designs,Computer Human Interface EEG sig
17、nals,Stock Index,Data Types fraud detection,Social Network Mining,Monitoring flu through twitter.Monitoring traffic through mobile calls.,Entity Cube,34,Experimental Economics,Vernon L. Smith,for having established laboratory experiments as a tool in empirical economic analysis, especially in the st
18、udy of alternative market mechanisms” From http:/nobelprize.org/,Behavior Economics Irrational Agents,Notable for his work on the psychology of judgments and decision making, behavioral economics. Winning $10 or $1000 with chance of 1%.Losing $10 or $1000 with chance of 1%,Software Agents for Tradin
19、g,What is the capital of China?What is the population of Beijing?What is the population of the capital of China?,Reasoning with Natural Language,Evolutionary Computing,Genetic AlgorithmSir Richard Dawkins “The selfish Genes”,Stochastic Optimization,Cellular Automaton,Wolfram was educated atEton. At
20、the age of 15, he published an article onparticle physics4and enteredOxford Universityat age 17. He wrote a widely cited paper on heavyquarkproduction at age 18.2Wolfram received hisPh.D.in particle physics from theCalifornia Institute of Technologyat age 205and joined the faculty there. He became h
21、ighly interested incellular automataat age 21.2Wolframs work in particle physics, cosmology and computer science earned him one of the firstMacArthur awards.,Decision Trees,P(h|e) = P(e|h)P(h)/P(e)A Proof that everyone can understandP(h, e) = P(h|e) P(e)P(e, h) = P(e|h) P(h),Bayesian Statistics,Grap
22、hical Model of Gaussian Distribution and Hiearachical Structure with Latent Variables,Understanding Semantics,Demographics MS AdCenter Lab,Commercial Intentions of Given Website,If you want to sell one, what is the best price?,N97 (Nokia Phone),Minority Game,There are more than1 00 Irish music lover
23、s but El Farol has only 60 seats. The show is enjoyable only when fewer than 60 people show up. Every people should decide weekly whether go to the bar to enjoy live music in the risk of staying in a crowd place or stay at home.,The rules are simple: a finite number of players have to choose between
24、 two sides; whoever ends up in the minority side is a winner.,Simplified from market aiming to analyze complex financial market,Collective Behavior Decomposition,Simulation Results (Li, Ma and Qin, 2010 ),Ying Ma, Guanyi Li, Yingsai Dong and Zengchang Qin (2010), Minority game data mining for market
25、 predictions, for Stock Market Predictions, to appear in the Proceedings of AAMAS 2010. Guanyi Li, Ying Ma, Yingsai Dong and Zengchang Qin (2010), Behavior learning in minority games, To appear in the Proceedings of CARE 2009. Zengchang Qin, Marcus Thint and Zhiheng Huang (2009), Ranking answers by
26、hierarchical topic models, Proceedings of IEA/AIE 2009, LNCS 5579, pp. 103-112, Springer.Zhiheng Huang, Marcus Thint and Zengchang Qin (2008), Question classification using head words and their hypernyms, The Proceedings of Conference on Empirical Methods on Natural Language Processing, pp. 927-936, ACL.,References,Non-academic,Academic AI,Fuzzy Logic and Logic of Science,NLP & ANN,GA, ALIFE & Multi-agent,Web: or Google “Zengchang Qin” for my LinkedIn Profiles.,Contact Information,Thank you very much!Any questions?,
