Lec1-AIIntro (1).ppt
- 1. Artificial Intelligence Computational Intelligence Alien Intelligence? Summer 2004 Dennis Kibler
- 2. Course Mechanics • 4 quizzes: each 15% of grade • 2 coding assignment+3 handin homeworks • Lowest of these dropped + 40% of grade • Cheating = F in course • Lectures notes online – see my web page • Current notes and homeworks ok • Future notes/homeworks under revision
- 3. Today’s Lecture • Goal: what’s AI about anyway? • Read Chapter 1 • A brief history • The state of the art • Three key ideas: – Search, Representation/Modeling, Learning
- 4. AI Hypothesis The Brain is a Computer What are the computational principles? How can we find them out? How will we know if we succeed? Analogy: Birds fly but we don’t build planes with feathers and flapping wings.
- 6. Questions to Ponder • How can you measure intelligence? • What capabilities would you expect for a robot servant? • Which is harder, playing chess or picking up egg?
- 7. Reductionism: AI Topics • intelligent agents: step towards robots • search and game-playing • logical systems planning systems • uncertainty---probability and decision theory • learning language perception robotics philosophical issues
- 8. What is AI? • Thinking humanly • Thinking rationally • Acting humanly • Acting rationally • R&N vote for rationality (bounded)
- 9. Alan Turing • Father of AI • Conversation Test • Chess • Math • Language • Machine Intelligence – 1950
- 10. Acting humanly: The Turing test Turing (1950) ``Computing machinery and intelligence'': ``Can machines think?'' ``Can machines behave intelligently?'' Operational test for intelligent behavior: the Imitation Game Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for 5 minutes (Loebner Prize) Suggested major components of AI: knowledge reasoning language understanding learning
- 11. Thinking humanly: Cognitive Science • 1960s ``cognitive revolution'': • Information-processing psychology replaced behaviorism • Requires scientific theories of internal activities of the brainal • -- What level of abstraction? ``Knowledge'' or ``circuits''? • -- How to validate? Requires • 1) Predicting and testing behavior of human subjects (top-down) • or 2) Direct identification from neurological data (bottom-up) • Both approaches (roughly, Cognitive Science and Cognitive Neuroscience) are now distinct from AI
- 12. Thinking rationally: Laws of Thought • Normative or prescriptive rather than descriptive • Aristotle: what are correct arguments/thought processes? • Several Greek schools developed various forms of logic • Boole thought he would stop war • Direct line through mathematics and philosophy to modern AI • Problems: • 1) Not all intelligent behavior is mediated by logical deliberation • 2) What is the purpose of thinking? What thoughts should I have? Goals?
- 13. Acting rationally • Rational behavior: doing the right thing • The right thing: that which is expected to maximize goal achievement, • given the available information • Doesn't necessarily involve thinking---e.g., blinking reflex- --but • thinking should be in the service of rational action • Aristotle (Nicomachean Ethics): • Every art and every inquiry, and similarly every action and pursuit, is thought to aim at some good
- 14. Rational agents • An agent is an entity that perceives and acts • This course is about designing rational agents • Abstractly, an agent is a function from percept histories to actions: • For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance • Caveat: computational limitations make perfect rationality unachievable • So design best program for given machine resources. • Bounded Rationality
- 15. AI Prehistory • Philosophy – logic, methods of reasoning – mind as physical system – foundations of learning, language, rationality • Mathematics – formal representation and proof – algorithms – computation, (un)decidability, (in)tractability – probability – operations research
- 16. • Psychology – Adaptation – phenomena of perception and motor control – experimental techniques (psychophysics, etc.) • Linguistics – knowledge representation – grammar • Neuroscience – physical substrate for mental activity • Control theory – homeostatic systems, stability – simple optimal agent designs
- 17. AI History • 1943 McCulloch & Pitts: Boolean circuit model of brain • 1950 Turing's ``Computing Machinery and Intelligence'' • 1952--69 Look, Ma, no hands! • 1950s Early AI programs, including Samuel's checkers program, • Newell & Simon's Logic Theorist, • Gelernter's Geometry Engine • 1956 Dartmouth meeting: ``Artificial Intelligence'' adopted
- 18. History • 1965 Robinson's complete algorithm for logical reasoning • 1966--74 AI discovers computational complexity • Neural network research almost disappears • 1969--79 Early development of knowledge-based systems • 1980--88 Expert systems industry booms
- 19. History • 1988--93 Expert systems industry busts: ``AI Winter'' • 1985--95 Neural networks return to popularity – Discovery of BackPropagation • 1988-- Resurgence of probabilistic and decision-theoretic methods • Turn towards Mathematics
- 20. State of the art • Which of the following can be done at present? • Play a decent game of table tennis • Drive along a curving mountain road • Drive in the center of Cairo • Play a decent game of bridge • Discover and prove a new mathematical theorem • Write an intentionally funny story • Give competent legal advice in a specialized area of law • Translate spoken English into spoken Swedish in real time
- 21. Course in a nutshell • Problem Solving – State-space Representation plus Search • Deductive Reasoning – Logical representation plus search • Reasoning with Uncertainty – Probabilistic Models plus search • Learning – Many models plus search
- 22. Why Search • NLP: search grammar • Game Playing: search alternatives • Speech Understanding: search phoneme combinations • Learning: search models to explain data • Theorem Proving: search axioms/theorems • Diagnosis: search plausible conclusions
- 23. • What's needed?
- 24. Open vs Closed Tasks • Natural language understanding • Teaching chess • Image understanding • Learning to program • Robot to wash dishes • Achieveable? • NL front end to database • Playing chess • Identifying zip codes • Learning to diagnosis known diseases • Robot to distribute mail (mobots) • All achievable