* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download Introduction to AI - Dr Shahriar Bijani
Survey
Document related concepts
Agent (The Matrix) wikipedia , lookup
Wizard of Oz experiment wikipedia , lookup
Technological singularity wikipedia , lookup
Artificial intelligence in video games wikipedia , lookup
Visual Turing Test wikipedia , lookup
Human–computer interaction wikipedia , lookup
Computer Go wikipedia , lookup
Knowledge representation and reasoning wikipedia , lookup
Computer vision wikipedia , lookup
Intelligence explosion wikipedia , lookup
Existential risk from artificial general intelligence wikipedia , lookup
Embodied cognitive science wikipedia , lookup
Philosophy of artificial intelligence wikipedia , lookup
Transcript
ARTIFICIAL INTELLIGENCE INTRODUCTION TO ARTIFICIAL INTELLIGENCE Dr. Shahriar Bijani Shahed University Spring 2017 OUTLINE What is AI? A brief history Predictions and Reality Shahed University, Spring 2017 Course overview Introduction to AI 2 COURSE OVERVIEW Introduction to AI Introduction Shahed University, Spring 2017 and Agents (chapters 1,2) Search (chapters 3,4,5,6) Logic (chapters 7,8,9) Knowledge Representation (chapter 10) Planning (chapters 11,12) Uncertainty (chapters 13,14) Learning (chapters 18,20) Natural Language Processing (chapter 22,23) Other Topics (Neural Nets, ….) 3 FOUND ON THE WEB … Introduction to AI AI is the reproduction of the methods of human reasoning or perception Intelligent Using computational models to simulate intelligent behavior (human) behavior and processes Computer AI is the study of mental abilities through the use computational methods Shahed University, Spring 2017 Humans 4 Introduction to AI WHAT IS AI? Act like humans Act rationally Think like humans Think rationally Shahed University, Spring 2017 Discipline that systematizes and automates intellectual tasks to create machines that: 5 Introduction to AI ACT LIKE HUMANS The Shahed University, Spring 2017 goal of AI is to create computer systems that perform functions that are assumed to require intelligence when done by humans Methodology: Take a task at which people are better, e.g.: Prove a theorem Play chess Plan a surgical operation Diagnose a disease Navigate in a building and make a computer do it 6 ACT LIKE HUMANS : TURING TEST Alan Turing (1950) "Computing machinery and intelligence": "Can machines think?" "Can machines behave intelligently?" Operational test for intelligent behavior: the simulation game The computer is asked questions by a human interviewer. It passes the test if the interviewer or cannot tell whether the responses come from a person Shahed University, Spring 2017 Introduction to AI 7 ACT LIKE HUMANS : TURING TEST Required capabilities: natural language processing, knowledge representation, automated reasoning, learning Shahed University, Spring 2017 Introduction to AI No physical interaction total Turing Test, needs computer vision & robotics 8 Think like humans Think rationally Shahed University, Spring 2017 Discipline that systematizes and automates intellectual tasks to create machines that: Act like humans Act rationally Introduction to AI WHAT IS AI? 12 THINKING HUMANLY: COGNITIVE How the computer performs functions does matter Comparison of the traces of the reasoning steps (cognitive science) 1960s "cognitive revolution": information-processing psychology Cognitive science: computer models (from AI) + experiments from Psychology Requires scientific theories of internal activities of the brain, by: 1) Predicting and testing behavior of human subjects (top-down) or 2) Direct identification from neurological data (bottom-up) Shahed University, Spring 2017 Introduction to AI MODELING Both approaches (roughly, Cognitive Science and Cognitive Neuroscience) are now distinct from AI But, do we want to duplicate human imperfections? 13 DISCOURSE ON THE METHOD, BY DESCARTES (1598-1650) Introduction to AI Shahed University, Spring 2017 If there were machines which bore a resemblance to our bodies and imitated our actions as closely as possible for all practical purposes, we should still have two very certain means of recognizing that they were not real men. The first is that they could never use words, or put together signs, as we do in order to declare our thoughts to others… Secondly, even though some machines might do some things as well as we do them, or perhaps even better, they would inevitably fail in others, which would reveal that they are acting not from understanding, … 14 DISCOURSE ON THE METHOD, BY DESCARTES (1598-1650) Introduction to AI Shahed University, Spring 2017 If there were machines which bore a resemblance to our bodies and imitated our actions as closely as possible for all practical purposes, we should still have two very certain means of recognizing that they were not real men. The first is that they could never use words, or put together signs, as we do in order to declare our thoughts to others… Secondly, even though some machines might do some things as well as we do them, or perhaps even better, they would inevitably fail in others, which would reveal that they are acting not from understanding, … 15 DISCOURSE ON THE METHOD, BY DESCARTES (1598-1650) Introduction to AI Shahed University, Spring 2017 If there were machines which bore a resemblance to our bodies and imitated our actions as closely as possible for all practical purposes, we should still have two very certain means of recognizing that they were not real men. The first is that they could never use words, or put together signs, as we do in order to declare our thoughts to others… Secondly, even though some machines might do some things as well as we do them, or perhaps even better, they would inevitably fail in others, which would reveal that they are acting not from understanding, … 16 Think like humans Think rationally Shahed University, Spring 2017 Discipline that systematizes and automates intellectual tasks to create machines that: Act like humans Act rationally Introduction to AI WHAT IS AI? 17 THINKING RATIONALLY: "LAWS OF THOUGHT" 1. 2. It is not easy to state informal knowledge in the formal terms required by logical notation (particularly when it is less than 100% certain). There is a big difference between being able to solve a problem "in principle" and doing so in practice. Shahed University, Spring 2017 Aristotle: what are correct arguments/thought processes? Logicians developed various forms of logic: notation and rules of derivation for thoughts; By 1965, programs existed that could solve any problem described in logical notation. Problems: Introduction to AI 18 Think like humans Think rationally Shahed University, Spring 2017 Discipline that systematizes and automates intellectual tasks to create machines that: Act like humans Act rationally Introduction to AI WHAT IS AI? 19 ACTING RATIONALLY: RATIONAL AGENT Introduction to AI Shahed University, Spring 2017 Rational behavior: doing the right thing The right thing: that which is expected to maximize goal achievement, given the available information Doesn't necessarily involve thinking – e.g., blinking reflex – but thinking should be in the service of rational action 20 RATIONAL AGENTS For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance computational limitations make perfect rationality unachievable design best program for given machine resources Shahed University, Spring 2017 agent is an entity that perceives and acts This course is about designing rational agents Abstractly, an agent is a function from percept histories to actions: [f: P* A] Introduction to AI An 21 AI PREHISTORY Mathematics algorithms, (in)tractability, Economics Neuroscience Psychology Computer engineering Control theory Linguistics Logic, methods of reasoning, mind as system foundations of learning, language, rationality Formal representation and proof computation, (un)decidability, probability utility, decision theory physical substrate for mental activity phenomena of perception and motor control, experimental techniques building fast computers design systems that maximize an objective function over time knowledge representation, grammar Shahed University, Spring 2017 Philosophy physical Introduction to AI 25 SHORT HISTORY OF AI 1965 1966—73 1969—79 1980-1986-1987-1995-2003-- McCulloch & Pitts: Boolean circuit model of brain Turing's "Computing Machinery and Intelligence" Dartmouth meeting: "Artificial Intelligence" adopted Look, Ma, no hands! Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine Robinson's complete algorithm for logical reasoning AI discovers computational complexity Neural network research almost disappears Early development of knowledge-based systems AI becomes an industry Neural networks return to popularity AI becomes a science The emergence of intelligent agents 26 Human-level AI back on the agenda Shahed University, Spring 2017 1943 1950 1956 1952—69 1950s Introduction to AI A SHORT HISTORY OF AI 1940-1950: Early days 1943: McCulloch & Pitts: Boolean circuit model of brain 1950: Turing's “Computing Machinery and Intelligence” 1950—70: Excitement: Look, Ma, no hands! 1950s: Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: “Artificial Intelligence” adopted 1965: Robinson's complete algorithm for logical reasoning 1970—90: Knowledge-based approaches 1990—: Statistical approaches 1969—79: Early development of knowledge-based systems 1980—88: Expert systems industry booms 1988—93: Expert systems industry collapse: “AI Winter” Reappearance of probability, focus on uncertainty General increase in technical depth Agents and learning systems… “AI Spring”? 2000—: Human-level AI back on the agenda A BRIEF HISTORY General problem solving (GPS) Theorem proving Games Formal calculus Shahed University, Spring 2017 The name “Artificial Intelligence” is coined. Early period (50’s to late 60’s): Basic principles and generality Introduction to AI 1956: 28 Birth of AI occurred when Marvin Minsky & John McCarthy organized the Dartmouth Conference in 1956 brought together researchers interested in "intelligent machines" for next 20 years, all advances in AI were by following Minsky (MIT), McCarthy (MIT/Stanford), Newell & Simon (Carnegie),… John McCarthy Marvin Minsky Shahed University, Spring 2017 Introduction to AI A BRIEF HISTORY :THE ORIGINS OF AI 29 Shahed University, Spring 2017 1969-1971: Shakey the robot (Fikes, Hart, Nilsson) Logic-based planning (STRIPS) Motion planning (visibility graph) Inductive learning (PLANEX) Computer vision Introduction to AI A BRIEF HISTORY 30 A BRIEF HISTORY period (late 60’s to mid Focus on narrow tasks requiring expertise Encoding of expertise into rules, such as: If A car has ▪ off-highway tires and ▪ 4-wheel drive and ▪ high ground clearance Then the car can traverse difficult terrain (0.8) Knowledge engineering Japanese 5th generation computer project CYC system Shahed University, Spring 2017 80’s): Introduction to AI Knowledge-is-Power 31 A BRIEF HISTORY becomes an industry (80’s – present): Shahed University, Spring 2017 Expert systems: Digital Equipment, Teknowledge, Intellicorp, Du Pont, oil industry, … Lisp machines: LMI, Symbolics, … Constraint programming: ILOG Robotics: Adept, Fanuc, ABB, Sony, Honda, iRobot, Evolution Robotics Voice processing Video games Fraud detection, image analysis, medical diagnosis, … Introduction to AI AI 32 A BRIEF HISTORY Introduction to AI Shahed University, Spring 2017 The return of neural networks, genetic algorithms, and artificial life (80’s – 90’s) Increased connection with economics, probabilistic modeling, and control theory (90’s – present) - AI is less philosophical, more technical - AI is a major source of computational techniques for complex systems 33 PREDICTIONS AND REALITY … (1/3) Shahed University, Spring 2017 the 60’s, a famous AI professor from MIT said: “At the end of the summer, we will have developed an electronic eye” Up to now, there is still no general computer vision system capable of understanding complex dynamic scenes But computer systems routinely perform road traffic monitoring, facial recognition, medical image analysis, part inspection, motion capture, … Introduction to AI In 34 PREDICTIONS AND REALITY … (2/3) This prediction became true in 1998 AI techniques (search, planning, probabilistic reasoning) are used in many video games Shahed University, Spring 2017 1958, Herbert Simon (CMU) predicted that within 10 years a computer would be Chess champion Introduction to AI In 35 Shahed University, Spring 2017 In the 70’s, many believed that computer-controlled robots would soon be everywhere from manufacturing plants to home Introduction to AI PREDICTIONS AND REALITY … (3/3) 36 Shahed University, Spring 2017 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 Introduction to AI PREDICTIONS AND REALITY … (3/3) 37 Shahed University, Spring 2017 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 (are rolling) on Mars, fly autonomously, Introduction to AI PREDICTIONS AND REALITY … (3/3) 38 Introduction to AI Shahed University, Spring 2017 39 Shahed University, Spring 2017 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 (are rolling) on Mars, fly autonomously, while others perform brain and heart surgery … Introduction to AI PREDICTIONS AND REALITY … (3/3) 40 (http://world.honda.com/news/2001/c011112.html) Shahed University, Spring 2017 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 (are rolling) on Mars, fly autonomously, while others perform brain and heart surgery … and humanoid robots are available for rent Introduction to AI PREDICTIONS AND REALITY … (3/3) 41 NATURAL LANGUAGE Speech technologies (e.g. Siri) Automatic speech recognition (ASR) Text-to-speech synthesis (TTS) Dialog systems Language processing technologies Question answering Machine translation Web search Text classification, spam filtering, etc… VISION (PERCEPTION) Object and face recognition Scene segmentation Image classification Demo1: VISION – lec_1_t2_video.flv Images from Erik Sudderth (left), wikipedia (right) Demo2: VISION – lec_1_obj_rec_0.mpg Demo 1: ROBOTICS – soccer.avi Demo 2: ROBOTICS – soccer2.avi Demo 3: ROBOTICS – gcar.avi ROBOTICS Robotics Technologies Part mech. eng. Part AI Reality much harder than simulations! Vehicles Rescue Soccer! Lots of automation… In this class: We ignore mechanical aspects Methods for planning Methods for control Images from UC Berkeley, Boston Dynamics, RoboCup, Google Demo 4: ROBOTICS – laundry.avi Demo 5: ROBOTICS – petman.avi LOGIC Logical systems Theorem provers NASA fault diagnosis Question answering Methods: Deduction systems Constraint satisfaction Satisfiability solvers (huge advances!) Image from Bart Selman GAME PLAYING Classic Moment: May, '97: Deep Blue vs. Kasparov Open question: First match won against world champion “Intelligent creative” play 200 million board positions per second Humans understood 99.9 of Deep Blue's moves Can do about the same now with a PC cluster How does human cognition deal with the search space explosion of chess? Or: how can humans compete with computers at all?? 1996: Kasparov Beats Deep Blue “I could feel --- I could smell --- a new kind of intelligence across the table.” 1997: Deep Blue Beats Kasparov “Deep Blue hasn't proven anything.” Huge game-playing advances recently, e.g. in Go! Text from Bart Selman, image from IBM’s Deep Blue pages DECISION MAKING Applied AI involves many kinds of automation Scheduling, e.g. airline routing, military Route planning, e.g. Google maps Medical diagnosis Web search engines Spam classifiers Automated help desks Fraud detection Product recommendations … Lots more! DESIGNING RATIONAL AGENTS An agent is an entity that perceives and acts. A rational agent selects actions that maximize its (expected) utility. Characteristics of the percepts, environment, and action space dictate techniques for selecting rational actions Sensors Percepts ? Actuators Actions Environment This course is about: General AI techniques for a variety of problem types Learning to recognize when and how a new problem can be solved with an existing technique Agent PAC-MAN AS AN AGENT Agent Sensors Environment Percepts ? Actuators Actions Pac-Man is a registered trademark of Namco-Bandai Games, used here for educational purposes Demo1: pacman-l1.mp4 or L1D2 54