CS 561: Artificial Intelligence � Instructor: Prof Hadi Moradi � Instructor: Prof. Hadi Moradi, moradi@usc.edu � Lectures: M-Th 09:00-10:40, OHE136 � Office hours: MW 2:30 – 4:00 pm, SAL310, � Or by appointment O b i � TAs: Jeong-Yoon Lee � SAL 112 � Office hours: TTH 1:00-2:30 � Email: jeongyol@usc.edu CS 561: Artificial Intelligence � Course web page: � http:/ / www-scf.usc.edu/ ~ csci561a � Up to date information, lecture notes � Relevant dates, links, etc. � Also you may check http://den.usc.edu � Class format: two sections of 45 minutes � Course material: � Course material: � [AIMA] Artificial I ntelligence: A Modern Approach, by Stuart Russell and Peter Norvig. 2 nd edition 1
CS 561: Artificial Intelligence � Course overview: foundations of symbolic Course overview: foundations of symbolic intelligent systems. Agents, search, problem solving, logic, representation, reasoning, symbolic programming, probabilistic reasoning, and robotics. � Prerequisites: CS 455x, i.e., � programming principles, discrete mathematics for computing, software design and software engineering concepts. Some knowledge of C/C+ + for some programming assignments. CS 561: Artificial Intelligence � Grading: Grading: � 25% for midterm � 25% for final � 40% for homeworks and projects � 10% for Quizzes 10% f Q i 2
Practical issues � Class list: use learn.usc.edu Class list: use learn usc edu � Login with your USC username and password � I f CSCI 561A is not listed as your courses, notify the TA. ot y t e � Submissions: See class web page under Assignments submit -user csci561 -tag HW3 HW3.tar.gz Administrative Issues � Midterm 1: 7 /26/10 9:00 - 10:40pm Midterm 1: 7 /26/10 9:00 10:40pm � Midterm 2: 8 /10/10 9:00 - 10:40pm See also the class web page: http://den.usc.edu/ http://den usc edu/ 3
Why study AI? Search engines Science Medicine/ Diagnosis Labor What else? Appliances Humanoid Robots: From Honda to Sony Walk Turn http://world.honda.com/robot/ Stairs 4
Sony AIBO movie1 http://www.aibo.com Natural Language Question Answering http://aimovie.warnerbros.com http://www.ai.mit.edu/projects/infolab/ 5
Robot Teams USC robotics Lab Modular robots self re-assembly. What is AI? The exciting new effort to make “The study of mental faculties The exciting new effort to make The study of mental faculties computers thinks … machine through the use of computational with minds, in the full and models” (Charniak et al. 1985) literal sense” (Haugeland 1985) “The art of creating machines A field of study that seeks to that perform functions that explain and emulate intelligent require intelligence when require intelligence when behavior in terms of behavior in terms of performed by people” computational processes” (Kurzweil, 1990) (Schalkol, 1990) 6
AI – The Bigger Picture ? Computer Science Philosophy p y Artificial Intelligence Cognitive Science (Psychology) Robotics Neuroscience ? (Engineering) (Biology) Acting Humanly: The Turing Test � Alan Turing's 1950 article Computing Machinery � Alan Turing s 1950 article Computing Machinery and Intelligence discussed conditions for considering a machine to be intelligent 7
Acting Humanly: The Turing Test What tasks require AI? “AI is the science and engineering of AI is the science and engineering of � making intelligent machines which can perform tasks that require intelligence when performed by humans …” � What tasks require AI? 8
What tasks require AI? � Tasks that require AI: q � Solving a differential equation � Brain surgery � Inventing stuff � Playing Jeopardy � Playing Wheel of Fortune � What about walking? � What about grabbing stuff? � What about pulling your hand away from fire? � What about watching TV? � What about day dreaming? Acting Humanly: The Full Turing Test • • Problem: Problem: 9
What would a computer need to pass the Turing test? � Communication: Communication: � Memory: � Reasoning: � Learning: What would a computer need to pass the Turing test? � Sensing: Sensing: � Motor control (total test): M t t l (t t l t t) 10
Thinking Humanly: Cognitive Science � 1960 Cognitive Revolution : 1960 “Cognitive Revolution”: information-processing psychology replaced behaviorism Thinking Humanly: Cognitive Science � Cognitive science and modeling the activities Cognitive science and modeling the activities of the brain � What level of abstraction? “Knowledge” or “Circuits”? � How to validate models? 11
Thinking Rationally: Laws of Thought � Aristotle (~ 450 B.C.) attempted to codify Aristotle ( 450 B.C.) attempted to codify “right thinking” � What are correct arguments/thought processes? Thinking Rationally: Laws of Thought � Problems: 12
Acting Rationally: The Rational Agent � Rational behavior: Doing the right thing! � Provides the most general view of AI because it includes: Acting Rationally: The Rational Agent � Advantages: Advantages: 13
How to achieve AI? � How is AI research done? � Theoretical � Experimental How to achieve AI? � There are two main lines of research: There are two main lines of research: � Biological, study humans and imitate their psychology or physiology. � phenomenal, study and formalize common sense facts about the world and the problems that the world presents to the achievement of goals. world presents to the achievement of goals. � The two approaches interact to some extent, and both should eventually succeed. It is a race, but both racers seem to be walking. [ John McCarthy] 14
Branches of AI � Logical AI � Search � Natural language processing � pattern recognition � Knowledge representation � I nference From some facts, others can be inferred. , � Automated reasoning � Learning from experience � Planning To generate a strategy for achieving some goal AI Prehistory 15
Brief History of AI Ancient Times 384 B.C. - Aristotle Thought - Logic: The science of knowing. Next time - implement links - Middle Age 1200 Ramon Lull Ars Magnus: a rule-based device to model man's behavior and nature tionally:Laws of T Renaissance Renaissance - Empiricism Empiricism Explanation of processes 17 th Century - Gottfried Leibniz - 1st system of formal logic - 18 th Century Rene Descartes Dualism 19 th Century 1845 - Charles Babbage - Analytical Engine - - George Boole - - Formalization of the Laws of Logic Formalization of the Laws of Logic Thinking Rat - 1879-1903 - Gottlob Frege - First-order predicate calculus - Early 20 th 1910-1912 - Russel-Whitehead Century - Principia Mathematica - Bertrand Russel 1931 - Kurt Godel - Incompleteness Theorem of Logic - Roots of AI in Science: � Aristotle(b.384-): syllogism – formal reasoning � Ramon Lull (b.1235): Ars Magna – a machine capable of answering all questions � Rene Descartes (1596): mind / body separation (dualism); "cogito ergo sum“ � Wilhelm Liebniz (1646-1716): a mechanical concept generator; "materialism" g ; � Charles Babbage(1792-1871), Ada Lovelace (1815-1860): Analytical Engine – a general-purpose calculator � George Boole(1815-1864): logic algebras - logical encoding and calculation of thoughts � Gottlob Frege(1848-1925): predicate calculus 16
Birth of Artificial Intelligence 1940-1956 - 1942 - ENIAC :First digital computer - - 1943 - Mc Culloch and Pitts - Artificial neural network - 1945 - J. Von Neumman - Modern computer architecture - - 1949 - Claude Shannon Grea - Use of heuristics to solve complex - problems at Expectations 1950 - Alan M.Turing - Computing Machinery and - Intelligence: - Turing Test 1955 - Herbert Simon,Alan Newell 1 st AI program:Logic Theorist - - Herbert Simon 1956 - Dartmouth Conference - - The Beginning of AI � McCulloch & Pitts � developed theory of artificial neurons (precursor to ANN's) – 1943 � Alan Turing – "Can Machines Think?" � the turing test (1950) � the turing machine � Marvin Minsky & Dean Edmonds � first ANN constructed, 1951 � John McCarthy � convened the Dartmouth conference that coined the term artificial intelligence (AI) (1956) and set the research agenda � symbolic AI � connectionism � LISP (list processing) 1958 1 st AI language 17
The Rise of AI 1957- 1960’s - 1958 - John McCarthy . - LISP - 1960 - Marvin Minsky - Theory of Frames - 1961 - Herbert Simon,Alan Newell - GPS:General Problem Solver - Growing - Herbert Simon 1962 - Frank Rosenblatt - Perceptron: - Learning in Neural Networks g Disenchantment 1965 1965 - Lotfi A. Zadeh L tfi A Z d h - Fuzyy Logic - Fuzzy Sets - 1968 Joseph Weizenbaum ELIZA : simulates diagnosis by a psychiatrist. 1969 - Marvin Minsky,Seymour Papert - Limitations of Perceptrons - S. Papert An Optimistic Start In the 50's, 60's and early 70's, much exciting progress was being made in AI: � Chess � Claude Shannon, 1950 � The Logic Theorist � Alan Newell, Cliff Shaw, Herb Simon, 1957 � Checkers (Machine Learning) � Arthur Samuels, 1959 � Eliza - NLP � Joseph Weizenbaum, 1966 � DENDRAL – Knowledge-Based System � Feigenbaum, Buchanan, Lederberg, 1969 � SHRDLU – NLP (Blocks World) � Terry Winnograd, 1972 � GPS (General Problem Solver) � Alan Newell & Herb Simon, 1972 18
Recommend
More recommend
