1. Copyright, 2005 All rights reserved L. Manevitz1 Artificial Intelligence Background and Overview L. Manevitz

2. Copyright 2006 All rights reserved L. Manevitz2 Artificial Intelligence-What is it? HAL -2001 Je pense dont je suis !

3. Copyright 2006 All rights reserved L. Manevitz3 Requirements Two – three projects (obligatory) Final Final Grade – between 33% - 67% projects (probably 40 - 50%) Late projects will be penalized Attendance in Lectures is strongly recommended

4. Copyright 2006 All rights reserved L. Manevitz4 Text and References Texts: (on reserve) –Elaine Rich Artificial Intelligence –Nils Nilsson Artificial Intelligence –Patrick Winston Artificial Intelligence –Newer Books: –Russell & Norvig Artificial Intelligence: A Modern Approach –Nils Nilsson Artificial Intelligence:A New Synthesis -Webber & Nilsson Readings in Artificial Intelligence.

5. Copyright 2006 All rights reserved L. Manevitz5 What is Artificial Intelligence? How do we define it? What is it good for? History ? Successes/ Failures? Future Outlook? http://www-formal.stanford.edu/jmc/whatisai/whatisai.html

6. Copyright 2006 All rights reserved L. Manevitz6 Possible Examples? Chess? Recognizing Credit Card Fraud? Automatic Train Driver? Automatic Car Driver? Recommender System? Agents in a Computer Game? Boy Robot in movie “AI”? Emotions? Solving Geometry Problems? Proving Theorems? Giving Directions? Answering Questions for Registering Students?

7. Copyright 2006 All rights reserved L. Manevitz7 What is intelligence ? Eureka !

8. Copyright 2006 All rights reserved L. Manevitz8 How do we define it? What is artificial intelligence? What is natural intelligence? How do we know if we achieve it?

9. Copyright 2006 All rights reserved L. Manevitz9 Psychology How do humans and animals think and act? Cognitive Psychology and Cognitive Science Behaviorism

10. Copyright 2006 All rights reserved L. Manevitz10 Neuroscience How does the Brain Work? Compare with Computer? –10**11 neurons vs 1 CPU (10**8 gates) –10 **-3 sec vs 10 **-10 sec –10**14 bits/sec vs 10**10 bits/sec –Moore’s Law (doubles every 1.5 years) CPU gate count will equal neurons in 2020. –Does this mean anything?

11. Copyright 2006 All rights reserved L. Manevitz11 Mathematics Formal Rules to Draw Conclusions What can be Computed? –Godel’s Theorem –NP completeness How to Reason with Uncertain Information? Probability Game Theory

12. Copyright 2006 All rights reserved L. Manevitz12 Are the Means Important? Black Box – raw power versus “cleverness” Or White Box - somehow models how people work Or White Box – somehow cleverness sneaks in by some over-riding idea?

13. Copyright 2006 All rights reserved L. Manevitz13 Is Adaptivity (learning) Crucial?

14. Copyright 2006 All rights reserved L. Manevitz14 Artificial Intelligence Goals. Methods. Examples.

15. Copyright 2006 All rights reserved L. Manevitz15 Goals in A.I. Understand thinking. Make computers perform tasks that require intelligence if performed by people. “Asking if a computer can think is like asking if a submarine can swim.” Dijkstra

16. Copyright 2006 All rights reserved L. Manevitz16 Goals in A.I. Main Goal : Artificial intelligence. Sub Goal : Understanding human intelligence and how it is possible. Related subjects : Neurophysiology Cognitive Psychology (Artificial Neural Networks)

17. Copyright 2006 All rights reserved L. Manevitz17 What sort of Functionality Is Needed? To act humanly? (See Turing Test) –Natural language processing –Knowledge Representation –Automated Reasoning –Machine Learning –Decisions under uncertainty –Computer Vision –Robotics –Speech Recognition

18. Copyright 2006 All rights reserved L. Manevitz18 What sort of Functionality Is Needed? To act humanly? (See Turing Test) To think humanly? (See Cognitive Science) Needs Human tests To think rationally? –Logic and logicist tradition –Game Theory and Rationality Act Rationally? –(Back to Turing Test); limited rationality? –Environment Important

19. Copyright 2006 All rights reserved L. Manevitz19

20. Copyright 2006 All rights reserved L. Manevitz20 AI Supplements Philosophy, Psychology, Linquistics, etc. 1)Use of computer metaphors has led to rich language for talking and thinking about thinking. 2)Computer models force precision. 3)Computer implementations quantify task requirements. 4)Computer programs can be experimented on in ways that animal brains can not.

21. Copyright 2006 All rights reserved L. Manevitz21 Aspects Engineering : Solve “real world” problems using ideas about knowledge representation and handling. Scientific : Discover ideas about knowledge that helps explain various orts of intelligence.

22. Copyright 2006 All rights reserved L. Manevitz22 State of the Art NASA Mars Robots (planning program) Game Playing: Deep Blue & Junior, etc Autonomous Control and Learning –Alvinn (CMU) drove across the USA (98% of the time) Medical Diagnosis Programs –state of art AI Planning handles US logistics (“repaid all DARPA expenditures ever” from ’91 Gulf War”) Robotics Assistant Surgery Language Understanding and Problem Solvers Recognizing Cognitive Actions by Looking at Brain Scans!

23. Copyright 2006 All rights reserved L. Manevitz23 Applications Farming robots, Manufacturing, Medical, Household. Data mining, Scheduling, Risk Management Control, Agents. Internet + AI : natural laboratory

24. Copyright 2006 All rights reserved L. Manevitz24 Physical Symbol Hypothesis (Newell) : A physical symbol system has the necessary and sufficient means for intelligent action. This hypothesis means that we can hope to implement this in the computer. Note : Use of term “intelligent action” not “intelligence”. Compare with Searle “Chinese Room”. Underlying Hypothesis Underlying Hypothesis

25. Copyright 2006 All rights reserved L. Manevitz25 Definitions of AI “Science of making machines do things that would require intelligence if done by man.” M. Minsky “… make computers more useful and to understand principles that make intelligence possible” P. Winston

26. Copyright 2006 All rights reserved L. Manevitz26 Definitions of AI cont. “… main tenet that there are common processes underlie thinking … these can be understood and studied scientifically … unimportant who is doing thinking – man or computer. This is an implementation detail.” N. Nilsson

27. Copyright 2006 All rights reserved L. Manevitz27 Some History Literature: Golem, Frankenstein, Odysseus, Asimov, … Rules of Thought: Greeks (Aristotle, correctness of proofs), Formal Systems (Aristotle, Saadia Gaon), Leibniz, Boole, Godel, Turing. Note two aspects: Physical and Mental (corresponds to Robotics and AI today)

28. Copyright 2006 All rights reserved L. Manevitz28 Some History Babylonians Greeks – Plato, Aristotle, Greek Mythology Arabic Culture – Saadia Gaon, AlKhwarzi Frankenstein, Golem Analytical Engine, Babbage, Lovelace Mechanical Calculation and Mechanical Proof - Pascal, Leibniz, Hilbert WWII : Turing, von Neumann, Godel, ACE, Einiac Artificial Neuron Dartmouth (Modern AI) Distributed Agents, Internet Machine Learning

29. Copyright 2006 All rights reserved L. Manevitz29 What sort of Functionality Is Needed? To act humanly? (See Turing Test) To think humanly? (See Cognitive Science) Needs Human tests To think rationally? –Logic and logicist tradition –Game Theory and Rationality Act Rationally? –(Back to Turing Test); limited rationality? –Environment Important

30. Copyright 2006 All rights reserved L. Manevitz30 What sort of Functionality Is Needed? To act humanly? (See Turing Test) –Natural language processing –Knowledge Representation –Automated Reasoning –Machine Learning –Decisions under uncertainty –Computer Vision –Robotics –Speech Recognition

31. Copyright 2006 All rights reserved L. Manevitz31 1940s Turing, Shannon, Von Neumann. 1950s –1960s Learning Machines; Naïve Translators,Naïve Chess Programs, (Simon’s 10 year prediction) Perceptrons. 1960s – 1970s MIT, Stanford,Carnegie-Mellon,(Minsky, McCarthy, Simon) General Purpose Algorithms. 1980s Multi-level Perceptrons,Expert Systems, Knowledge Based Systems, Logical AI, Uncertainty Reasoning. 1990s NN applications, Theory of Learning, Agent Paradigm,Internet Applications,Space Robots,Computer Chess Champion. 2000s SVM and Kernel Learning, Mixed applications, multiple agent interactions and game theory

32. Copyright 2006 All rights reserved L. Manevitz32 Overall Approaches to AI Solve Global Problem – Try to pass Turing Test – philosophical Solve Specific Problems in Areas – also make things useful; engineering, experimental; find anything that works Solve things by mimicing human cognition; experiments with humans Solve things by mimicing physical processes; neuroscience, evolution, understanding randomness

33. Copyright 2006 All rights reserved L. Manevitz33 Spin-offs of A.I. The Computer. Formal Mathematical Logic. Much of Mathematics. Time Sharing. Computer Languages. Computer Vision. Expert Systems Theory of Learning Data Mining. Soft bots. Expert Systems Robotics. Video Display. Information retrieval. Machine Learning Computer Games

34. Copyright 2006 All rights reserved L. Manevitz34 Spin-offs of A.I. cont. Data Mining. Soft bots. Expert Systems Robotics. Video Display. Information retrieval.

35. Copyright 2006 All rights reserved L. Manevitz35 Problems addressed by A.I. Game playing. Theorem proving. Perception (Vision, Speech). Natural Language Understanding.

36. Copyright 2006 All rights reserved L. Manevitz36 Problems addressed by A.I. cont. Expert Problem Solving : –Symbolic Mathematics. –Medical Diagnosis. –Chemical Analysis. –Engineering Design. Intelligent Agents. Automated Negotiation. Data Mining. Web Search.

37. Copyright 2006 All rights reserved L. Manevitz37 Artificial Intelligence Expert Systems. Vision. Speech. Language. Games. Planning and Action. Theories of Knowledge. Neural Networks.

38. Copyright 2006 All rights reserved L. Manevitz38 Fields of Application Expert Systems. Language Understanding. Robotics. Automated Negotiation. Internet Retrieval. Educational Tools. Software Assistants.

39. Copyright 2006 All rights reserved L. Manevitz39 Give examples of Expert Systems Xcon System Pressure Air Pressure Differential Equations

40. Copyright 2006 All rights reserved L. Manevitz40 Methodologies Algorithmic (e.g. vision …). Heuristic (games, expert systems). Linguistic, Semantics (speech, language understanding). Symbolic Manipulation (most subjects). Logical Systems (formal) Game Theoretic.

41. Copyright 2006 All rights reserved L. Manevitz41 Methodologies cont. Truth Maintenance Systems. Fuzzy Logic (knowledge representation, expert systems). “Knowledge Engineering” (expert systems). Neural Networks (learning-non-symbolic representations). Baysean Analysis + related (uncertainty processing) Learning Systems and learning theory.

42. Copyright 2006 All rights reserved L. Manevitz42 Types of programs in A.I. Theoretically all programming languages and computers are equivalent. Practically there are huge differences in efficiency, even possibility NP-complete problems. Languages: –LISP – very flexible. –PROLOG – designed to fit “back tacking”, “resolution”, expert systems. Methodology : –Heuristic vs. Algorithmic.

43. Copyright 2006 All rights reserved L. Manevitz43 Algorithm : A recipe (set of instructions) which when followed always gives the correct solution. Feasible Algorithm : An algorithm which can in fact be implemented in such a way that the solution can be found in a reasonable time.

44. Copyright 2006 All rights reserved L. Manevitz44 Heuristic : a set of instructions which one has reason to believe will often give reasonably correct answers.

45. Copyright 2006 All rights reserved L. Manevitz45 Heuristic vs. Algorithmic Heuristic : Rules of the thumb. No guarantee. Algorithmic : Guarantee correct results.

46. Copyright 2006 All rights reserved L. Manevitz46 Why use heuristic ? Many problems either : –Can be proven to have no algorithm : Theorem proving. Halting problem. –Can be proven to have no feasible algorithm : NP-complete. Traveling salesman. Scheduler. Packing. –No algorithm is known although one exists : Chess.

47. Copyright 2006 All rights reserved L. Manevitz47 Examples of heuristics functions Chess : –No. of my pieces – No. of opponents. –Weighted values of pieces. –Positional ideas. Traveling Salesman : –Comparison with neighbors.

48. Copyright 2006 All rights reserved L. Manevitz48 Algorithmic Aspects Undecidable Problems. Infeasible Problems. People versus NP-complete.

49. Copyright 2006 All rights reserved L. Manevitz49 Other Techniques General Search and Matching Algorithms Representations of Knowledge – (See book by E.Davis : Naïve Physics, – Conceptual Dependencies (Schank), –Object Oriented –Models of Memory: Kanerva, Anderson, Grossberg Logic (See LICS conferences) –Automatic Theorem Proving –Non-Traditional Logics Non-monotonic Logics Circumscription Closed World Assumption Prolog Ex: Surprise Quiz Paradox Dealing with Time Uncertainty Natural Language Speech Vision Learning Neural Network Approach

50. Copyright 2006 All rights reserved L. Manevitz50 Other Techniques (cont) Dealing with Time –Logics: Temporal and Modal –Noise in Neural Networks Uncertainty –Baysean Networks (Pearl) (Microsoft assistant) –Combination Formulas Dempster-Shafer Fuzzy Logics Hummel-Landy-Manevitz Mycin, etc –Independence Assumptions and Weakenings Natural Language Speech VisionHigh Level; low level Learning Inductive, Genetic Algorithms, Learning Theory Neural Network Approach: Representation, Learning Other Machine Learning Approaches

51. Copyright 2006 All rights reserved L. Manevitz51 Philosophy Is there any possibility of AI?(Searle, Dreyfuss, Symbol Manipulation Assumption, Godel’s Theorem, Consciousness). What would it mean to have AI? Turing Test: Makes Sense or Not?

52. Copyright 2006 All rights reserved L. Manevitz52 Turing Test computer person tester

53. Copyright 2006 All rights reserved L. Manevitz53 Searle’s Chinese Box English workers Chinese Chinese References