Hong Cheng http://www.se.cuhk.edu.hk/~hcheng SEG4560 Computational Intelligence for Decision Making Chapter 1: Introduction Hong Cheng http://www.se.cuhk.edu.hk/~hcheng 11/05/2019 Computational Intelligence for Decision Making

Computational Intelligence for Decision Making SEG4560 Course home page: http://www.se.cuhk.edu.hk/~hcheng/seg4560 Textbook: S. Russell and P. Norvig Artificial Intelligence: A Modern Approach Prentice Hall, 2003, Second Edition Instructor: Hong Cheng Tutor: Yang Zhou Assessment: Assignments (30%), Midterm exam (30%) Final exam (40%) 11/05/2019 Computational Intelligence for Decision Making

Computational Intelligence for Decision Making Outline Course overview What is AI? A brief history The state of the art 11/05/2019 Computational Intelligence for Decision Making

Computational Intelligence for Decision Making Course overview Introduction and Agents (chapters 1,2) Search (chapters 3,4,5,6) Logic (chapters 7,8,9) Planning (chapters 11,12) Uncertainty (chapters 13,14) Learning (chapters 18,20) Natural Language Processing (chapter 22,23) Human beings are the most intelligent species on the planet. For thousands of years, people have tried to understand how we think, that is, how we perceive, understand, predict and manipulate the world. The field of ai goes still further: it attempts not just to understand, but also to build intelligent entities. AI is one of the newest sciences. Work started right after world war II, and the name itself was coined in 1956. AI is a big field. Includes logic, probability, and continuous mathematics; perception, reasoning, learning and action; from microelectronic devices to robotic planetary explorers. The main theme is the idea of an intelligent agent. Define AI as the study of agents that receive percepts from the environment and perform actions. Each such agent implements a function that maps percept sequences to actions. Eight parts. 1. offers a view of AI based on the idea of intelligent agents– systems that decide what to do and then do it. 2. problem solving, or search in particular, concentrates on methods for deciding what to do when one needs to think ahead several steps– for example, playing chess. 3. knowledge and reasoning, or logic, discusses ways to represent knowledge about the world – how it works, what it is currently like and what one’s actions might do– and how to reason logically with that knowledge. 4. Planning discusses how to use the reasoning methods to decide what to do. 5. Uncertain knowledge and reasoning, is analogous to 3 and 4, but concentrates on reasoning and decision making in the presence of uncertainty about the world. 6. learning, describes methods for generating the knowledge required by these decision-making components. 7. Communicating, perceiving and acting, or NLP in particular, describes ways in which an intelligent agent can perceive its environment so as to know what is going on, whether by vision, touch, hearing, or understanding language, and ways in which it can turn its plans into real actions. Finally, the conclusions part analyzes the past and future of AI and the philosophical and ethical implications of AI. 11/05/2019 Computational Intelligence for Decision Making

Computational Intelligence for Decision Making What is AI? Views of AI fall into four categories: Systems that think Systems that think like humans rationally Systems that act Systems that like humans act rationally The textbook advocates "acting rationally" The definitions vary along two dimensions: the ones on top are concerned with thought processes and reasoning, whereas the ones on the bottom address behavior. The definitions on the left measure success in terms of fidelity to human performance, whereas the ones on the right measure against an ideal concept of intelligence, which we will call rationality. A tension exists between the human-centered approach and the rationality-centered approach. A human-centered approach must be an empirical science, involving hypothesis and experimental confirmation. A rationalist approach involves a combination of mathematics and engineering. Let’s look at the four approaches in more detail. 11/05/2019 Computational Intelligence for Decision Making

Acting humanly: Turing Test Turing (1950) "Computing machinery and intelligence": "Can machines think?"  "Can machines behave intelligently?" Operational test for intelligent behavior: the Imitation Game Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for 5 minutes Anticipated all major arguments against AI in following 50 years Suggested major components of AI: knowledge, reasoning, language understanding, learning The turing test is based on indistinguishability from human beings. The human interrogator poses some written questions. If he cannot tell whether the written responses come from a human or an AI system. Then the computer passes the test. To pass the test, the computer needs to possess the following capabilities: 11/05/2019 Computational Intelligence for Decision Making

Thinking humanly: cognitive modeling 1960s "cognitive revolution": information-processing psychology replaced prevailing orthodoxy of behaviorism Requires scientific theories of internal activities of the brain -- How to validate? Requires 1) Predicting and testing behavior of human subjects (top-down) or 2) Direct identification from neurological data (bottom-up) Both approaches (roughly, Cognitive Science and Cognitive Neuroscience) are now distinct from AI Both share with AI the following characteristic: The available theories do not explain (or engender) anything resembling human-level general intelligence If we are going to say that a given program thinks like a human, we must have some way of determining how humans think. Once we have a sufficiently precise theory of the human mind, it becomes possible to express the theory as a computer program. The interdisciplinary field of cognitive science brings together computer models from AI and experimental techniques from psychology to try to construct precise and testable theories of the workings of the human mind. Real cognitive science is necessarily based on experimental investigation of actual humans or animals. In the early days, there was often confusion between AI and cognitive science. 11/05/2019 Computational Intelligence for Decision Making

Thinking rationally: "laws of thought" Aristotle: what are correct arguments/thought processes? Several Greek schools developed various forms of logic: notation and rules of derivation for thoughts; may or may not have proceeded to the idea of mechanization Direct line through mathematics and philosophy to modern AI Problems: Not all intelligent behavior is mediated by logical deliberation What is the purpose of thinking? What thoughts should I have? These laws of thought were supposed to govern the operation of the mind; their study initiated the field called logic. Logicians in the 19th century developed a precise notation for statements about all kinds of things in the world and about the relations among them. By 1965, programs existed that could in principle solve any solvable problem described in logical notation. The logicist tradition within artificial intelligence hopes to build on such programs to create intelligent systems. 11/05/2019 Computational Intelligence for Decision Making

Acting rationally: rational agent 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 In the laws of thought approach to AI, the emphasis was on correct inferences. Making correct inferences is sometimes part of being a rational agent, because one way to act rationally is to reason logically to the conclusion that a given action will achieve one’s goals and then act on that conclusion. On the other hand, correct inference is not all of rationality, because there are often situations where there is no provably correct thing to do, yet something must still be done. There are also ways of acting rationally that cannot be said to involve inference. 11/05/2019 Computational Intelligence for Decision Making

Computational Intelligence for Decision Making Rational agents An 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] For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance Caveat: computational limitations make perfect rationality unachievable  design best program for given machine resources The view of rational agents, or “act rationally” has two advantages: 1. it is more general than the “laws of thought” approach, because correct inference is just one of several possible mechanisms for achieving rationality. 2. it is more amenable to scientific development than are approaches based on human behavior or human thought because the standard of rationality is clearly defined and completely general. 11/05/2019 Computational Intelligence for Decision Making

Computational Intelligence for Decision Making AI prehistory Philosophy Logic, methods of reasoning, mind as physical system foundations of learning, language, rationality Mathematics Formal representation and proof algorithms, computation, (un)decidability, (in)tractability, probability Economics utility, decision theory Neuroscience physical substrate for mental activity Psychology phenomena of perception and motor control, experimental techniques Computer building fast computers engineering Control theory design systems that maximize an objective function over time Linguistics knowledge representation, grammar 11/05/2019 Computational Intelligence for Decision Making

Computational Intelligence for Decision Making Abridged history of AI 1943 McCulloch & Pitts: Boolean circuit model of brain 1950 Turing's "Computing Machinery and Intelligence" 1956 Dartmouth meeting: "Artificial Intelligence" adopted 1952—69 Look, Ma, no hands! 1950s Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine 1965 Robinson's complete algorithm for logical reasoning 1966—73 AI discovers computational complexity Neural network research almost disappears 1969—79 Early development of knowledge-based systems 1980-- AI becomes an industry 1986-- Neural networks return to popularity 1987-- AI becomes a science 1995-- The emergence of intelligent agents 2003-- Human-level AI back on the agenda 11/05/2019 Computational Intelligence for Decision Making

Computational Intelligence for Decision Making State of the art Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997 Proved a mathematical conjecture (Robbins conjecture) unsolved for decades No hands across America (driving autonomously 98% of the time from Pittsburgh to San Diego) During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people NASA's on-board autonomous planning program controlled the scheduling of operations for a spacecraft Proverb solves crossword puzzles better than most humans A few applications of AI. The computer vision system was trained to steer a car to keep it following a lane. A human took over the other 2%, mostly at exit ramps. It has video cameras that transmit road images, then computes the best direction to steer, based on experience from previous training runs. And had to account for starting points, destinations, routes, and conflict resolution among all parameters. It generates plans from high level goals specified from the ground and monitored the operation of the spacecraft as the plans were executed. Proverb uses a large database of past puzzles, and a variety of information sources including dictionaries and online databases such as movies and actors. 11/05/2019 Computational Intelligence for Decision Making