AI Introduction PDF

# Introduction * What is AI? * The foundations of AI * A brief history of AI * The state of the art ## What is AI? - definition * **Intelligence:** "ability to learn, understand and think" (Oxford dictionary) * AI is the study of how to make computers make things which at the moment people do bet...

# Introduction * What is AI? * The foundations of AI * A brief history of AI * The state of the art ## What is AI? - definition * **Intelligence:** "ability to learn, understand and think" (Oxford dictionary) * AI is the study of how to make computers make things which at the moment people do better. * **Examples:** Speech recognition, Smell, Face, Object, Intuition, Inferencing, Learning new skills, Decision making, Abstract thinking ## AI Definitions * A broad field which means different things to different people * Concerned with getting computers to do tasks that require human intelligence This image shows that there are many tasks for which it seems like humans require intelligence. However, computers can do these tasks _without_ even thinking, such as complex arithmetic or recognizing a face. On the other hand, there are many tasks that people do without conscious thought that are still very difficult to automate. ## What is AI? This image shows a 2x2 table. Across the top, it says: * Thinking humanly * Thinking rationally Down the side, it says: * Acting humanly * Acting rationally It then explains that the top row is concerned with thought processes and reasoning, and the second row addresses behavior. ## Do human behavior is rational? * A system is rational, if it does the right thing, given what it knows * We can distinguish human and rational behavior and say, human are not rational, i.e., Irrational (emotionally unstable) * However, we are not perfect * Ex: Not everyone gets same grade (A) on the exam ## AI Definitions This image shows a table that categorizes AI approaches into four categories: ### Think like human * The exciting new effort to make computers think ... machines with minds, in the full and literal sense. [Haugeland 85]. ### Act humanly * The study of how to make computers do things at which, at the moment, people are better. [Rich & Knight, 1991] ### Think Rationally * The study of the computations that make it possible to perceive, reason, and act. [Winston, 1992] ### Act rationally * The branch of computer science that is concerned with the automation of intelligent behavior. [Luger and Stubblefield, 1993] ## 1. Systems that act like humans * The overall behaviour of the system should be human like. * It could be achieved by observation. ## 1. Acting Humanly: The Turing Test * Alan Turing (1912-1954) * "Computing Machinery and Intelligence" (1950) This image shows a diagram of the Turing Test. A human interrogator is in a room with a teletype connection to two other people: a human and an AI system. The interrogator asks the same questions to both people and tries to determine which is which. If the interrogator cannot tell them apart, the AI system is considered to be intelligent. ## Turing Test This image shows another diagram of the Turing Test. A human tester is shown talking on the phone. One end of the phone is connected to a computer and the other end is connected to a person. * You enter a room which has a computer terminal. * You have a fixed period of time to type what you want into the terminal, and study the replies. * At the other end of the line is either a human being or a computer system. * If it is a computer system, and at the end of the period you cannot reliably determine whether it is a system or a human, then the system is deemed to be intelligent. ## Recognizing AI * The Turing test is one criterion, but it's controversial, as: * It's an imitation game, in which a human interrogator is isolated in a room, with teletype connections to an unseen human and an unseen computer * The interrogator asks the same questions of the human and the machine and tries to determine which is which * If the interrogator can't tell them apart, the computer is intelligent * The Turing test has positive features: * It's objective and unbiased * It's independent of how the machine operates * There are no agreed upon alternative tests * The Turing test also has negative features: * It overlooks aspects of intelligence such as perception and mobility * It overlooks human intelligence * It can be gimmicky and detract from serious AI research efforts * What is the the amount of knowledge that a machine would need to pass the Turing Test? ## What sort of Functionality Is Needed? * To act humanly? * Natural language processing * Knowledge Representation * Automated Reasoning * Machine Learning * Computer Vision * Robotics ## Act Like Human To act humanly, the computer would need: * **Natural Language Processing** for communication. * **Knowledge Representation** to store information before and during interrogation. * **Automated Reasoning** to answer questions and draw new conclusions. * **Machine learning** to adapt to new circumstances. * **Computer vision** to perceive objects * **Robotics** to manipulate objects and move about ## Turing test * **Turing test** avoided physical interaction between the interrogator and the computer. * **Turing test** involves first four aspects (1-4) This image shows that the **Total Turing test** includes a video signal so that the interrogator can test the perceptual abilities as well as to pass physical object. * **Total Turing test** involves last two aspects (5-6) ## 2. Think Like Human This image describes the **Cognitive Modeling approach** * To develop a program that think like human, the way the human think should be known. * Knowing the precise theory of mind (how human think?) → expressing the theory as a computer program. * **GPS (General Problem Solver)** [ by Newell & Simon, 1961] is an example of this approach. * Concerned with comparing the trace of its reasoning steps to traces of human subjects solving the same problem rather than correctly solve problems ## 2. Thinking Humanly: Cognitive Modelling * Not content to have a program correctly solving a problem. * More concerned with comparing its reasoning steps to traces of human solving the same problem. This image defines **Cognitive science** as the combining of Computer models from AI and Experimental techniques from psychology. * It results in the **Construction of human mind working theories** * **Requires testable theories of the workings of the human mind** * **Requires experimental investigation of actual humans or animals** **Note:** We will not pursue human mind theory here as we have only a computer for experimentation. ## 2. Systems that think like humans * Most of the time it is a black box where we are not clear about our thought process. * One has to know functioning of brain and its mechanism for possessing information. * It is an area of cognitive science. This image explains the following: * The stimuli are converted into mental representation. * Cognitive processes manipulate representation to build new representations that are used to generate actions. * Neural network is a computing model for processing information similar to brain. ## 3. Thinking Rationally: Laws of Thought * Aristotle was one of the first to attempt to codify "right thinking", i.e., irrefutable reasoning processes. ## 3. Think Rationally This image describes the **Law of Thought Approach** * **Aristotle and his syllogism (right thinking) : always gave correct conclusions given correct premises** * **Here is an example of a syllogism:** * Socrates is a Man. %Fact * All men are Mortal. % Rule if X is a Man then X is Mortal. * Therefore Socrates is Mortal. % Inference * These laws of thoughts initiated the field of LOGIC. * **Formal logic provides a precise notation and rules for representing and reasoning with all kinds of things in the world.** ## 3. Think Rationally * **Two main obstacles:** * Not easy to translate an informal knowledge into a formal logic. * Ex: when the knowledge is less than 100% certain * There is a difference between solving a problem "in principle" and solving it "in practice" * Ex: It is usually the case that problems with few hundred facts * Can exhaust the computational power of any computer. * So, it is required to have some guidance as to which reasoning steps to try first * **Note:** Both obstacles apply while building any computational reasoning systems. * Thus the need for heuristics. ## 4. Acting Rationally This image explains the **Rational Agent Approach** * Agent * agent is something that acts * **Computer agents** * Operate autonomously * perceive their environments * Persist over a prolonged time period * Adapt to change, create and pursue goals * **Rational agent** * Acts so as to achieve the best outcome or when there is uncertainty, the best expected outcome ## 4. Acting Rationally * Laws of thought approach vs. Act rationally * Laws of thought approach * Emphasis on correct inference * Making correct inferences is part of being rational agent This image states: **Act rationally = reason logically to the conclusion that a given action will achieve one's goals and then act on that conclusion.** ## 4. Acting Rationally * Correct inference is not always == rationality * Ex: even if there is no correct thing to do, something must be done * Hence, it means that there are also ways of acting rationally that cannot be said to involve inference * Ex: reflex actions (acting rationally without involving inference) * Fast action is required than careful deliberation ## 4. Acting Rationally This image lists **two main advantages of rational agent approaches:** * **More general than "the laws of thought" approach (correct inference is one of several possible mechanism to achieve rationality)** * **More amenable to scientific development than approaches based on human behavior/thought.** ## Rationality vs. human behavior * **The rationality is mathematically well defined, general (many agent design have been generated to achieve it)** * **Human behavior adapted for one specific environment, defined by sum total of all the things that humans do.**