AI

授課教師：顏士淨2013/09/12

1

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

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

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

Part V Learning

5

Part V Learning 18 Learning from Examples

19 Knowledge in Learning 20 Learning Probabilistic Models 21 Reinforcement Learning

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

What is AI?

7

Systems that… Thinking humanly? Thinking rationally? Acting humanly? Acting rationally?

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)

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

Problems

10

Not all intelligent behavior is medicated by logical deliberation

What is the purpose of thinking?

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:

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

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

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

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

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

AI prehistory(3/3)

Linguistics

knowledge representation

grammar

natural language processing

Control theory

homeostatic systems, stability

simple optimal agent designs

Computer engineering(1940-)

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

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”

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

State of the art

Autonomous planning and scheduling Game playing Autonomous control Diagnosis Logistics planning Robotics Language understanding and problem solving