Artificial Intelligence 22C 145
Popular in Course
Popular in ComputerScienence
This 21 page Class Notes was uploaded by Dr. Humberto Beier on Friday October 23, 2015. The Class Notes belongs to 22C 145 at University of Iowa taught by Staff in Fall. Since its upload, it has received 21 views. For similar materials see /class/228051/22c-145-university-of-iowa in ComputerScienence at University of Iowa.
Reviews for Artificial Intelligence
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 10/23/15
22c145 Artificial Intelligence Fall 2005 Introduction Cesare Tinelli The University of Iowa Copyright 200105 Cesare Tinelli and Hantao Zhang 8 8 These notes are copyrighted material and may not be used in other course settings outside of the University of Iowa in their current or modified form without the express written permission of the copyright holders 22c145 Artificial Intelligence Fall 05 p121 Texbook 8 Russell and P Norvig Arti cial Intelligence A Modern Approach Prentice Hall second edition 2003 Class Web Site wwwcsuiowaeduquottinellil45 Check the class web site daily Some slides and most of the figures are from our textbook 22c145 Artificial Intelligence Fall 05 p221 Other Al texts Title Authors Publisher Year AI A New Synthesis Nilsson Morgan Kaufmann 1998 Computational Intelligence Poole Mackworth Oxford 1998 Goebel Artificial Intelligence 3rd ed Winston AddisonWesley 1992 Artificial Intelligence 2nd ed Rich Knight McGrawHill 1991 AI Theory and Practice Dean Allen Benjamin Cummings 1995 Aloimonos Mathematical Methods in Al Bender IEEE Comp Press 1996 Logical Foundations of AI Genesereth Nilsson Morgan Kaufmann 1987 22c145 Artificial Intelligence Fall 05 p321 Course Overview Topic Chapters Intelligent Agents 1 2 Programming in OCaml Problem Solving and Search 3 4 Constraint Satisfaction 5 Knowledge Representation and Reasoning 7 8 Logical Inference 9 Planning 11 12 Uncertain Knowledge and Reasoning 13 14 Machine Learning 18 19 20 22c145 Artificial Intelligence Fall 05 p421 Prerequisites l The course will be selfcontained but an elementary background in CS and Math is required I Expect the class material to become a little technical at times I You will implement some of the techniques seen in class Programming assignments will be mostly in OCaml 22c145 Artificial Intelligence Fall 05 p521 Readings for This Lecture l Chap 1 of Russell and Norvig 2003 22c145 Artificial Intelligence Fall 05 p621 What is Artificial Intelligence A scientific and engineering discipline devoted to l understanding principles that make intelligent behavior possible in natural or arti cial systems I developing methods for the design and implementation of useful intelligent artifacts Pooe Maokworth Goebel 22c145 Artificial Intelligence Fall 05 p7l21 What is intelligence then 22c145 Artificial Intelligence Fall 05 p821 What is intelligence then l Fast thinking I Knowledge l Ability to pass as a human I Ability to reason logically l Ability to learn I Ability to perceive and act upon one s environment I Ability to play chess at grandmaster s level I 22c145 Artificial Intelligence Fall 05 p821 Acting Humanly The Turing test Turing 1950 Computing machinery and intelligence HUMAN lNTEFtFiOGATCIFt 22c145 Artificial Intelligence Fall 05 p921 Acting Humanly The Turing test I Can machines think a Can machines behave intelligently l Operational test for intelligent behavior the Imitation Game I Predicted that by 2000 a machine might have a 30 chance of fooling a lay person for 5 minutes l Anticipated all major arguments against Al in following 50 years I Suggested major components of Al knowledge reasoning language understanding learning Problem Turing test is not reproducible constructive or amenable to mathematical analysis 22c145 Artificial Intelligence Fall 05 p1021 Thinking Humanly Cognitive Science I 1960s cognitive revolution informationprocessing psychology replaced prevailing orthodoxy of behaviorism l Require scientific theories of internal activities of the brain I What level of abstraction Knowledge or circuits I How to validate It requires 1 Predicting and testing behavior of human subjects topdown Cognitive Science 2 Direct identification from neurological data bottomup Cognitive Neuroscience 22c145 Artificial Intelligence Fall 05 p1121 Thinking Rationally Laws of Thought Several Greek schools at the time of Aristotle developed various forms of logic I Notation and rules of derivation for thoughts They may or may not have proceeded to the idea of mechanization l Direct line through mathematics and philosophy to modern Al l Problems 1 Not all intelligent behavior is mediated by logical deliberation 2 What is the purpose of thinking What thoughts should I have 22c145 Artificial Intelligence Fall 05 p1221 Acting Rationally l Rational behavior doing the right thing that which is expected to maximize goal achievement given the available information I Doesn t necessarily involve thinking eg blinking reflex but thinking should be in the service of rational action I Aristotle Every art and every inquiry and similarly every action and pursuit is thought to aim at some good 22c145 Artificial Intelligence Fall 05 p1321 Rational Agents I An agent is an entity that perceives and acts I This course is about designing rational agents l Abstractly an agent is a function from percept histories to actions f 73 gt A For any given class of environments and tasks we seek the agent or class of agents with the best performance l Caveat computational limitations make perfect rationality unachievabe l Approach design best program for given machine resources 22c145 Artificial Intelligence Fall 05 p1421 Summary of Experts View of AI The exciting new effort to make computers think machines with minds in the full and literal sense Haugeland 1985 The automation of activities that we asso ci ate with human thinking activities such as decisionmaking problem solving learning Bellman 1978 The study of mental faculties through the use of computational models Chamiak and McDermott 1985 The study of the computations that make it possible to perceive reason and act Winston 1992 The art of creating machines that perform functions that require intelligence when per formed by people Kurzweil 1990 The study of how to make computers do things at which at the moment people are better Rich and Knight 1991 A eld of study that seeks to explain and emulate intelligent behavior in terms of computational processes Schalkoff 1990 The branch of computer science that is con cerned with the automation of intelligent behavior Luger and Stubble eld 1993 Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally 22c145 Artificial Intelligence Fall 05 p1521 Operational Definition of Al Systems that act like humans Turing test Systems that think like humans Cognitive Science Systems that think rationally Logicbased AI Systems that act rationally Rational Agents 22c145 Artificial Intelligence Fall 05 p1621 Al s Foundations PhHosophy Mathematics Psychology Economics Linguistics Neuroscience Control theory logic methods of reasoning mind as physical system foundations of learning language rationality formal representation and proof algorithms computation undecidabiity intractabiity probability adaptation perception and motor control experimental techniques formal theory of rational decisions knowledge representation grammar plastic physical substrate for mental activity homeostatic systems stability simple optimal agent designs 22c145 Artificial Intelligence Fall 05 p1721 Potted History of Al 1943 1950 19508 1956 1965 1966 74 1969 79 1980 88 1988 93 1985 95 1988 1995 McCulloch amp Pitts Boolean circuit model of brain Turing s Computing Machinery and lntelligence Early Al programs including Samuel s checkers program Newell amp Simon s Logic Theorist Gelernter s Geometry E Dartmouth meeting Artificial lntelligence adopted Robinson s complete algorithm for logical reasoning Al discovers computational complexity Neural network research almost disappears Early development of knowledgebased systems Expert systems industry booms Expert systems industry busts Al Winter Neural networks return to popularity Resurgence of probability general increase in technical c Nouvelle Al ALife GAs soft computing Agents agents everywhere 22c145 Artificial Intelligence Fall 05 p1821 State of the art Which of the following can be done at present ltgtltgtltgtltgtltgtltgtltgtltgtltgtltgtltgt Play a decent game of table tennis Drive along a curving mountain road Drive in the center of Cairo Buy a week s worth of groceries at Berkeley Bowl Buy a week s worth of groceries on the web 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 Perform a complex surgical operation 22c145 Artificial Intelligence Fall 05 p1921
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'