CS 460: Artificial IntelligenceSlide 2Practical issuesWhy study AI?Honda Humanoid RobotSony AIBONatural Language Question AnsweringRobot TeamsWhat is AI?Acting Humanly: The Turing TestSlide 11What tasks require AI?Slide 13Acting Humanly: The Full Turing TestSlide 15Slide 16What would a computer need to pass the Turing test?Slide 18Thinking Humanly: Cognitive ScienceThinking Rationally: Laws of ThoughtSlide 21Acting Rationally: The Rational AgentHow to achieve AI?Branches of AIAI PrehistoryAI HistoryAI State of the artCourse OverviewCourse Overview (cont.)Slide 30Slide 31Slide 32Slide 33Slide 34Slide 35Slide 36Slide 37Slide 38Slide 39Slide 40Slide 41A driving example: BeobotsSlide 43Slide 44Slide 45Slide 46Slide 47Slide 48PrototypeMajor issuesGeneral architectureSlide 52The task-relevance mapMore formally: how do we do it?OutlookCS 460, Lecture 1CS 460: Artificial Intelligence•Instructor: Prof. Laurent Itti, [email protected]•Lectures: Th 5:00-7:50, THH-208•Office hours: Mon 3:00 – 5:00 pm, HNB-30A, and by appointment•Course web page: http://iLab.usc.edu/classes/2003cs460 •Up to date information•Lecture notes •Relevant dates, links, etc.•Course material:•[AIMA] Artificial Intelligence: A Modern Approach, by Stuart Russell and Peter Norvig.CS 460, Lecture 1CS 460: Artificial Intelligence•Course overview: foundations of symbolic intelligent systems. Agents, search, problem solving, logic, representation, reasoning, symbolic programming, 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.•Grading: 35% for midterm +35% for final +30% for mandatory homeworks/assignmentsCS 460, Lecture 1Practical issues•Class mailing list:will be setup on the backboard system at learn.usc.edu•Submissions: See class web page under AssignmentsCS 460, Lecture 1Why study AI?Search enginesLaborScienceMedicine/DiagnosisAppliances What else?CS 460, Lecture 1Honda Humanoid RobotWalkTurnStairshttp://world.honda.com/robot/CS 460, Lecture 1Sony AIBOhttp://www.aibo.comCS 460, Lecture 1Natural Language Question Answeringhttp://www.ai.mit.edu/projects/infolab/http://aimovie.warnerbros.comCS 460, Lecture 1Robot TeamsUSC robotics LabCS 460, Lecture 1What is AI?The exciting new effort to make computers thinks … machine with minds, in the full and literal sense” (Haugeland 1985)“The art of creating machines that perform functions that require intelligence when performed by people” (Kurzweil, 1990)“The study of mental faculties through the use of computational models” (Charniak et al. 1985)A field of study that seeks to explain and emulate intelligent behavior in terms of computational processes” (Schalkol, 1990)Systems that think like humansSystems that think rationallySystems that act like humansSystems that act rationallyCS 460, Lecture 1Acting Humanly: The Turing Test•Alan Turing's 1950 article Computing Machinery and Intelligence discussed conditions for considering a machine to be intelligent•“Can machines think?”  “Can machines behave intelligently?”•The Turing test (The Imitation Game): Operational definition of intelligence.CS 460, Lecture 1Acting Humanly: The Turing Test•Computer needs to possess: Natural language processing, Knowledge representation, Automated reasoning, and Machine learning•Are there any problems/limitations to the Turing Test?CS 460, Lecture 1What tasks require AI?•“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?CS 460, Lecture 1•Tasks that require AI:•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?What tasks require AI?CS 460, Lecture 1Acting Humanly: The Full Turing Test•Alan Turing's 1950 article Computing Machinery and Intelligence discussed conditions for considering a machine to be intelligent•“Can machines think?”  “Can machines behave intelligently?”•The Turing test (The Imitation Game): Operational definition of intelligence.•Computer needs to posses:Natural language processing, Knowledge representation, Automated reasoning, and Machine learning•Problem: 1) Turing test is not reproducible, constructive, and amenable to mathematic analysis. 2) What about physical interaction with interrogator and environment?•Total Turing Test: Requires physical interaction and needs perception and actuation.CS 460, Lecture 1Acting Humanly: The Full Turing Test•Problem: 1) Turing test is not reproducible, constructive, and amenable to mathematic analysis. 2) What about physical interaction with interrogator and environment?CS 460, Lecture 1Acting Humanly: The Full Turing TestProblem: 1) Turing test is not reproducible, constructive, and amenable to mathematic analysis. 2) What about physical interaction with interrogator and environment?Trap doorCS 460, Lecture 1What would a computer need to pass the Turing test?•Natural language processing: to communicate with examiner. •Knowledge representation: to store and retrieve information provided before or during interrogation. •Automated reasoning: to use the stored information to answer questions and to draw new conclusions. •Machine learning: to adapt to new circumstances and to detect and extrapolate patterns.CS 460, Lecture 1What would a computer need to pass the Turing test?•Vision (for Total Turing test): to recognize the examiner’s actions and various objects presented by the examiner. •Motor control (total test): to act upon objects as requested. •Other senses (total test): such as audition, smell, touch, etc.CS 460, Lecture 1Thinking Humanly: Cognitive Science•1960 “Cognitive Revolution”: information-processing psychology replaced behaviorism•Cognitive science brings together theories and experimental evidence to model internal activities of the brain•What level of abstraction? “Knowledge” or “Circuits”?•How to validate models?•Predicting and testing behavior of human subjects (top-down)•Direct identification from neurological data (bottom-up)•Building computer/machine simulated