Transcript Slide 1
1 CS461: ARTIFICIAL INTELLIGENCE Computer Science Department Lecture 1: Introduction Syllabus 2 Goal of the course: 1. 2. 3. 4. 17-Jul-15 Understand the fundamental concepts of Artificial Intelligence Understand different methods of search and optimization in AI Able to develop small application using heuristic functions to solve any search problem in AI Understand the fundamental concept of logic in AI (Search Methods, Propositional logic, first order logic, Neural Network……) Computer Science Department Syllabus 3 Recommended Books: 1. “Artificial Intelligence: A modern approach” Stuart Russell, Peter Norvig, Prentice Hall, 2003 (new edition 2006) 2. “Artificial Intelligence In Perspective”, Bobrow 3. “Artificial Intelligence Illuminated” Ben Coppin, Jones and Bartlett illuminated Series, 2004 4. “Artificial Intelligence: A new synthesis” Morgan Kaufmann, 1998 17-Jul-15 by Daniel G. Nils Nilsson, Computer Science Department Syllabus 4 Grading MT1 MT2 Final exam 17-Jul-15 15% 15% 40% Computer Science Department What is AI? 5 • • • • • AI is the simulation of the intelligence human processes. AI is the reproduction of the methods or the results of human reasoning or intuition AI is the study of mental faculties by calculative and data-processing methods Use calculative models to simulate an intelligent behavior Machines imitating the human 17-Jul-15 Computer Science Department What is AI? 6 Getting computers to do the right thing based on their circumstances and what they know. 17-Jul-15 Computer Science Department What is AI? 7 Views of AI fall into four categories: 17-Jul-15 Thinking humanly Thinking rationally Acting humanly Acting rationally Computer Science Department Thinking humanly 8 The way in which the computer carries out the tasks is important Cognitive Science → theories that study the way human would think . The interdisciplinary field of cognitive science brings together computer models from AI and experimental techniques from psychology to try to construct precise and testable theories of the workings of the human mind. 17-Jul-15 Computer Science Department Turing Test 9 Turing (1950) was interested in the following question: Can machines think? But he immediately decides that answering this question directly is hopeless. The Element of the Test Are: • An interrogator (a person who will ask questions) • a computer (intelligent machine !!) • A person who will answer to questions • A curtain (separator) 17-Jul-15 Computer Science Department Acting humanly: Turing Test 10 Typed input/output only Any kind of question is fair. The player poses questions to the computer/other human. Can the player reliably distinguish the computer from the human? 17-Jul-15 Computer Science Department Passing the Test 11 Suggested major components of AI: knowledge, reasoning, language understanding, learning The computer would need to possess some capabilities: • Natural language processing: To communicate successfully. • Knowledge representation: To store what it knows or hears. • Automated reasoning: to answer questions and draw conclusions using stored information. • Machine learning: To adapt to new circumstances and to detect and extrapolate patterns. • Computer vision: To perceive objects. • Robotics to manipulate objects and move. 17-Jul-15 Computer Science Department Thinking rationally: "laws of thought" 12 Aristotle: what are correct arguments/thought processes? Several Greek schools developed various forms of logic: notation and rules of derivation for thoughts; may or may not have proceeded to the idea of mechanization Direct line through mathematics and philosophy to modern AI Problems: 1. 2. 17-Jul-15 Not all intelligent behavior is mediated by logical deliberation What is the purpose of thinking? What thoughts should I have? Computer Science Department Acting rationally: rational agent 13 • • Rational behavior: doing the right thing The right thing: that which is expected to maximize goal achievement, given the available information 17-Jul-15 Computer Science Department Applied Areas of AI 14 Game playing Speech and language processing Expert reasoning Planning and scheduling Vision Robotics 17-Jul-15 Computer Science Department Some Examples 15 Playing chess Driving on the highway Translating languages Recognizing speech Diagnosing diseases 17-Jul-15 Computer Science Department Playing Chess 16 Environment? Board Actions? Legal moves Doing the right thing? Moves that lead to wins 17-Jul-15 Computer Science Department Recognizing Speech 17 Environment Audio signal Knowledge of user Actions Choosing word sequences Doing the right thing Recovering the users words 17-Jul-15 Computer Science Department Diagnosing Diseases 18 Environment Patient information Results of tests Actions Choosing diseases Choosing treatments Doing the right thing Eliminating disease 17-Jul-15 Computer Science Department Translation 19 Environment Source text to be translated Actions Word sequences in target language Doing the right thing? Words that achieve the same effect Words that are faithful to the source 17-Jul-15 Computer Science Department Driving 20 Environment Restricted access highway Actions Accelerate, turn, navigate, other controls Doing the right thing Stay safe, get where you want to go, get there quickly 17-Jul-15 Computer Science Department 2005 DARPA Challenge 21 17-Jul-15 Computer Science Department 2007 Challenge 22 The DARPA Urban Challenge will feature autonomous ground vehicles executing simulated military supply missions safely and effectively in a mock urban area. Safe operation in traffic is essential to U.S. military plans to use autonomous ground vehicles to conduct important missions. DARPA will award prizes for the top three autonomous ground vehicles that compete in a final event where they must safely complete a 60mile urban area course in fewer than six hours. First prize is $2 million, second prize is $500,000 and third prize is $250,000. To succeed, vehicles must autonomously obey traffic laws while merging into moving traffic, navigating traffic circles, negotiating busy intersections and avoiding obstacles. 17-Jul-15 Computer Science Department