Published on April 30, 2008
Introduction to AI: Introduction to AI Russell and Norvig: Chapter 1 CMSC421 – Fall 2005 What is AI?: What is AI? Found on the Web …: Found on the Web … AI is the simulation of intelligent human processes AI is the reproduction of the methods or results of human reasoning or intuition AI is the study of mental faculties through the use computational methods Using computational models to simulate intelligent behavior Machines to emulate humans Why AI?: Why AI? Cognitive Science: As a way to understand how natural minds and mental phenomena work e.g., visual perception, memory, learning, language, etc. Philosophy: As a way to explore some basic and interesting (and important) philosophical questions e.g., the mind body problem, what is consciousness, etc. Engineering: To get machines to do a wider variety of useful things e.g., understand spoken natural language, recognize individual people in visual scenes, find the best travel plan for your vacation, etc. Weak vs. Strong AI: Weak vs. Strong AI Weak AI: Machines can be made to behave as if they were intelligent Strong AI: Machines can have consciousness subject of fierce debate, usually among philosophers and nay-sayers, not so much among AI researchers! E.g. recent Red Herring article and responses http://groups.yahoo.com/group/webir/message/1002 AI Characterizations: AI Characterizations Discipline that systematizes and automates intellectual tasks to create machines that: Act Like Humans: Act Like Humans AI is the art of creating machines that perform functions that require intelligence when performed by humans Methodology: Take an intellectual task at which people are better and make a computer do it Turing test Prove a theorem Play chess Plan a surgical operation Diagnose a disease Navigate in a building Turing Test: Turing Test Interrogator interacts with a computer and a person via a teletype. Computer passes the Turing test if interrogator cannot determine which is which. Loebner contest: Modern version of Turing Test, held annually, with a $100,000 prize. http://www.loebner.net/Prizef/loebner-prize.html Participants include a set of humans and a set of computers and a set of judges. Scoring: Rank from least human to most human. Highest median rank wins $2000. If better than a human, win $100,000. (Nobody yet…) Chess: Chess Name: Garry Kasparov Title: World Chess Champion Crime: Valued greed over common sense Humans are still better at making up excuses. © Jonathan Schaeffer Perspective on Chess: Pro: Perspective on Chess: Pro “Saying Deep Blue doesn’t really think about chess is like saying an airplane doesn't really fly because it doesn't flap its wings” Drew McDermott © Jonathan Schaeffer Perspective on Chess: Con: Perspective on Chess: Con “Chess is the Drosophila of artificial intelligence. However, computer chess has developed much as genetics might have if the geneticists had concentrated their efforts starting in 1910 on breeding racing Drosophila. We would have some science, but mainly we would have very fast fruit flies.” John McCarthy © Jonathan Schaeffer Think Like Humans: Think Like Humans How the computer performs functions does matter Comparison of the traces of the reasoning steps Cognitive science testable theories of the workings of the human mind Connection with Psychology General Problem Solver (Newell and Simon) Neural networks Reinforcement learning But: Role of physical body, senses, and evolution in human intelligence? Do we want to duplicate human imperfections? Think/Act Rationally: Think/Act Rationally Always make the best decision given what is available (knowledge, time, resources) Perfect knowledge, unlimited resources logical reasoning Imperfect knowledge, limited resources (limited) rationality Connection to economics, operational research, and control theory But ignores role of consciousness, emotions, fear of dying on intelligence AI Characterizations: AI Characterizations Discipline that systematizes and automates intellectual tasks to create machines that: History of AI: History of AI Jean-Claude Latombe: I personally think that AI is (was?) a rebellion against some form of establishment telling us “Computers cannot perform certain tasks requiring intelligence” Bits of History: Bits of History 1956: The name “Artificial Intelligence” was coined by John McCarthy. (Would “computational rationality” have been better?) Early period (50’s to late 60’s): Basic principles and generality General problem solving Theorem proving Games Formal calculus Bits of History: Bits of History 1969-1971: Shakey the robot (Fikes, Hart, Nilsson) Logic-based planning (STRIPS) Motion planning (visibility graph) Inductive learning (PLANEX) Computer vision Bits of History: Bits of History Knowledge-is-Power period (late 60’s to mid 80’s): Focus on narrow tasks require expertise Encoding of expertise in rule form: If: the car has off-highway tires and 4-wheel drive and high ground clearance Then: the car can traverse difficult terrain (0.8) Knowledge engineering 5th generation computer project CYC system (Lenat) Bits of History: Bits of History AI becomes an industry (80’s – present): Expert systems: Digital Equipment, Teknowledge, Intellicorp, Du Pont, oil industry, … Lisp machines: LMI, Symbolics, … Constraint programming: ILOG Robotics: Machine Intelligence Corporation, Adept, GMF (Fanuc), ABB, … Speech understanding Information Retrieval – Google, … Bits of History: Bits of History The return of neural networks, genetic algorithms, and artificial life (80’s – present) Increased connection with economics, operational research, and control theory (90’s – present) Predictions and Reality … (1/3): Predictions and Reality … (1/3) In the 60’s, a famous AI professor from MIT said: “At the end of the summer, we will have developed an electronic eye” As of 2002, there is still no general computer vision system capable of understanding complex dynamic scenes But computer systems routinely perform road traffic monitoring, facial recognition, some medical image analysis, part inspection, etc… Predictions and Reality … (2/3): Predictions and Reality … (2/3) In 1958, Herbert Simon (CMU) predicted that within 10 years a computer would be Chess champion This prediction became true in 1998 Today, computers have won over world champions in several games, including Checkers, Othello, and Chess, but still do not do well in Go Predictions and Reality … (3/3): Predictions and Reality … (3/3) In the 70’s, many believed that computer-controlled robots would soon be everywhere from manufacturing plants to home Today, some industries (automobile, electronics) are highly robotized, but home robots are still a thing of the future But robots have rolled on Mars, others are performing brain and heart surgery, and humanoid robots are operational and available for rent (see: http://world.honda.com/news/2001/c011112.html) Mistakes …: Mistakes … Often, the potential of a new field is over-estimated in its early age, but under-estimated over the longer term AI proponents have over-estimated the need for smart software, and under-estimated the feasibility and potential of large software systems based on massive coding effort Why is AI Hard?: Why is AI Hard? Simple syntactic manipulation is not enough Machine Translation Big project in 1957 following Sputnik launch Translation of Russian documents ‘The spirit is willing but the flesh is weak’ ‘The vodka is strong but the meat is rotten’ Eliza: Eliza ELIZA: A program that simulated a psychotherapist interacting with a patient Coded at MIT during 1964-1966 by Joel Weizenbaum. First script was DOCTOR. The script was a simple collection of syntactic patterns not unlike regular expressions Each pattern had an associated reply which might include bits of the input (after simple transformations (my your) Weizenbaum was shocked at reactions: Psychiatrists thought it had potential. People unequivocally anthropomorphized. Many thought it solved the NL problem. Try typing Meta-x doctor in Emacs. Recent Loebner Prize winner, http://www.alicebot.org/ Colby’s PARRY: Colby’s PARRY Kenneth Colby modeled a paranoid using the same techniques circa 1968. PARRY has basic emotions. If it gets angry, its replies become more hostile. In a Turing test, expert psychiatrists were unable to distinguish PARRY’s ramblings from those of real paranoids. H: Good afternoon. My name is Doctor Jones. P: Pleased to meet you. H: How are you? P: All right I guess. H: Could you tell me your name? P: Pat Smith. H: I though you might have some problems. P: I've been upset lately. H: By what? P: People get on my nerves sometimes. H: Tell me more. P: Do you know anything about bookies? ... Parry meets Eliza…: Parry meets Eliza… P: I don't understand your motives. E: Why don't you understand my motives? P: Shouldn't I be? E: Why do you say that just now? P: That's just the way it is. E: Suppose that's the way it were not. P: So? E: I am not sure I understand you fully. P: You harp on the same questions too much. E: What does that similarity suggest to you? P: I don't get you. E: Do you wish that you did get I? Why is AI Hard?: Why is AI Hard? Computational intractability AI goal defined before notion of NP-completeness people thought to solve larger problems we simply need larger/faster computers didn’t understand the notion of exponential growth ALL of the algorithms we will study will be computational intractable (NP-complete as best) in the WORST case … How does the fact that we are dealing with the REAL WORLD make solving these computationally challenging problems feasible IN PRACTICE? CMSC 421: CMSC 421 We will focus on the rational agents (“engineering”) paradigm Make computers act more intelligently techniques: search, learning, constraint satisfaction, decision theory tasks: perception, commonsense reasoning, planning Goals for Class: Goals for Class You will learn a bunch of tools that are useful for building useful, adaptive software… to solve fun and challenging problems These tools will be useful for you whether you go into AI research (basics that anyone should know) or any other discipline (oh, hey, that looks like the planning problems we studied way back in cmsc421) Help you separate hype from what’s easily achievable using existing tools (and avoid reinventing them!) Syllabus: Syllabus Representing knowledge Reasoning or using knowledge Learning or Acquiring knowledge Problem solving: Search Constraint satisfaction Game-playing Logic and Inference Planning Dealing with Uncertainty Uncertainy Belief networks Decision making under uncertainty Learning Supervised Statistical Reinforment Learning What you’re responsible for: What you’re responsible for Class participation, 5% expected to read material before class attend class (not just in body – class not for reading the news paper, web surfing, etc.) participate in in-class exercises Homework, 25% 6-8 written homeworks Programming Assignments, 20% 2-3 programming assignments Midterm, 25% In class, tentatively Oct. 18 Final, 30% Wed. Dec 21, 10:30 – 12:30 (note that this is last day of finals) See web page, http://www.cs.umd.edu/class/fall2005/cmsc421/ for details Quiz: Quiz Does a plane fly? Does a boat swim? Does a computer think? About Myself: About Myself PhD from the Stanford University 2001 (Learning Statistical Models from Relational Data) working w/ Daphne Koller Before that worked at NASA doing constraint-based planning for analyzing earth science data Before that worked as a software engineer at an expert systems company MS from UC Berkeley working w/ Stuart Russell Joined UMD December 2001 Research interests: probabilistic reasoning and machine learning Applications to data mining, databases, medicine, etc.