1. AI 授課教師：顏士淨 2013/09/12 1

2. Part I & Part II 2  Part I Artificial Intelligence 1 Introduction 2 Intelligent Agents Part II Problem Solving 3 Solving Problems by Searching 4 Beyond Classical Search 5 Adversarial Search 6 Constraint Satisfaction Problems

3. Part III 3  Part III Knowledge and Reasoning 7 Logical Agents 8 First-Order Logic 9 Inference in First-Order Logic 10 Classical Planning 11 Planning and Acting in the Real World 12 Knowledge Representation

4. Part IV 4  Part IV Uncertain Knowledge and Reasoning 13 Quantifying Uncertainty 14 Probabilistic Reasoning 15 Probabilistic Reasoning over Time 16 Making Simple Decisions 17 Making Complex Decisions

5. Part V Learning 5  Part V Learning  18 Learning from Examples 19 Knowledge in Learning 20 Learning Probabilistic Models 21 Reinforcement Learning

6. Part VII && Part VIII 6  Part VII Communicating, Perceiving, and Acting 22 Natural Language Processing 23 Natural Language for Communication 24 Perception 25 Robotics Part VIII Conclusions

7. What is AI? 7  Systems that…  Thinking humanly?  Thinking rationally?  Acting humanly?  Acting rationally?

8. Thinking Humanly: Cognitive Science 8  1960s ” cognitive revolution ”  Information-processing psychology replaced prevailing orthodoxy of behaviorism  Requires scientific theories of internal activities  How to validate? Requires  Predicting and testing behavior of human subjects(top-down)  Direct identification from neurological data(bottom-up)

9. Thinking Rationally: Laws of Thought 9  Aristotle:  what are correct arguments/thought processes?  Logic:  notation and rules of derivation for thoughts  Direct line thought mathematics and philosophy to modern AI

10. Problems 10  Not all intelligent behavior is medicated by logical deliberation  What is the purpose of thinking?

11. Acting Humanly: The Turing Test(1/2) 11  Turing(1950) “ Computing machinery and intelligence ”  “ Can machines think? ”  ” Can machines behave intelligently? ”  Operation test for intelligent behavior:

12. Acting Humanly: The Turing Test(2/2) 12  Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for 5 minutes  Anticipated all major arguments against AI in following 50 years  Suggested major components of AI: knowledge, reasoning, language understanding, learning  Watson

13. Acting Rationally 13  Rational behavior: doing the right thing  The right thing  That which is expected to maximize goal achievement, given the available information  Aristotle: 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: f: P *  A * 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  design best program for given machine resources

15. AI prehistory(1/3) * Philosophy(428 B.C.-) logic, methods of reasoning mind as physical system foundations of learning, language, rationality * Mathematics(800 B.C. -) Formal representation and proof algorithms, computation, (un) decidability probability

16. AI prehistory(2/3) * Psychology(1879-) adaptation cognitive science * Economics(1766-) formal theory of rational decisions Decision theory Game theory * Neuroscience(1861-) plastic physical substrate for mental activity

17. AI prehistory(3/3) * Linguistics knowledge representation grammar natural language processing * Control theory homeostatic systems, stability simple optimal agent designs * Computer engineering(1940-)

18. Potted history of AI(1/3) 1943 McCulloch&Pitts: Boolean circuit model of brain 1950 Turing’s “Computing Machinery and Intelligence: 1950s Early AI programs, including Samuel’s checkers program, Newell & Simon’s Logic Theorist, Gelernter’s Geometry Engine 1956 Dartmouth meeting: “Artificial Intelligence” adopted

19. Potted history of AI(2/3) 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 1988-93 Expert systems industry busts: “AI Winter”

20. Potted history of AI(3/3) 1985-95 Neural networks return to popularity 1988- Resurgence of probability; general increase in technical depth “Nouvelle AI”: ALife, GAs, soft computing 1995- Agents agents every where

21. State of the art * Autonomous planning and scheduling * Game playing * Autonomous control * Diagnosis * Logistics planning * Robotics * Language understanding and problem solving