ARTIFICIAL INTELLIGENCE

Transcription

1 1 ARTIFICIAL INTELLIGENCE Fabrizio Santini Comp 131 VERSION 1.1

2 2 Welcome to the Artificial Intelligence class What is the course about? Artificial Intelligence, when? Artificial Intelligence, what? Questions? TODAY ON AI

3 3 What is the course about? SECTION 01

4 What is the course about? TEACHING STAFF FABRIZIO SANTINI Professor MOHAMMAD KARIMZADEH Ph.D. Teaching Assistant Fabrizio.Santini@tufts.edu Mohammad.Karimzadeh@tufts.edu MONICA LYONS Undergraduate Teaching Assistant HOLT SPALDING Undergraduate Teaching Assistant Monica.Lyons@tufts.edu Holt.Spalding@tufts.edu BRIAN MONTAMBAULT Graduate Teaching Assistant Brian.Montambault@tufts.edu

5 What is the course about? WHAT YOU WILL LEARN Foundations of AI: Search Constraint Satisfaction Uncertain search Applications: Cognitive Architectures Societal and Ethical Concerns Classical AI: First-order logic Planning Probabilistic AI: Graphical models Probabilistic inference

6 What is the course about? COURSE GOALS By the end of the semester, you should be able to: Identify the major classical and modern AI paradigms, and explain how they relate to each other Analyze the structure of a given problem such that an appropriate paradigm in which to frame that problem can be chosen Implement a wide variety of both classical and modern AI algorithms

7 What is the course about? PREREQUISITES, SCHEDULE, AND MORE Prerequisites: Programming skills (languages of choice: C++, Java, Matlab, and more) Data structures Some discrete math Knowledge of basic probability theory Textbook: Artificial Intelligence: A Modern Approach, 3rd edition Stuart Russel and Peter Norvig (2010) Office hours: after every class Take-out-the-trash-hour (aka TOTT-hour): No question is too silly

8 What is the course about? WHAT S EXPECTED OF YOU Problem sets: 5 programming problem sets Homework: Reading assignments of sections of the textbook Quizzes: 4 quizzes as a combination of multiple choices and open-ended answers Grading: 40% problem sets, 60% tests

9 What is the course about? COMMUNICATIONS All course communication will happen through Piazza All course announcements will be made through Piazza If you have any questions about assignments or the topics covered in class, post them on Piazza and we will try to respond to them in a timely manner Please, read the syllabus for the Q&A etiquette! For any other private matter, send us a private message through Piazza

10 10 Artificial Intelligence, when? SECTION 02

11 The king stared at the figure in astonishment. It walked with rapid strides, moving its head up and down, so that anyone would have taken it for a live human being. The Artificer touched its chin, and it began singing, perfectly in tune. He touched its hand, and it began posturing, keeping perfect time. [ ] and over these again, muscles, bones and limbs with their joints, skin, teeth and hair, all of them artificial... Liezi text, 300BC Ref. to Yan Shi 1023 to 957BC The Liezi text (300BC) describes a sort of engineer, an 'artificer' named Yan Shi. Sometime around 1023 to 957 BC, Yan Shi presented a marvelous invention before the fifth king of the Chinese Zhou Dynasty, King Mu. Yan Shi had created a life sized automaton which was able to move and preform several impressive functions. Pamela McCorduck writes Artificial Intelligence in one form or another is an idea that has pervaded Western intellectual history, a dream in urgent need of being realized," expressed in humanity's myths, legends, stories, speculation and clockwork automatons.

12 Artificial Intelligence, when? ANTIQUITY TH BC 5 TH BC 1 ST 5 TH 10 TH 15 TH 19 TH >922BC* Yan Shi presented King Mu of Zhou with mechanical men. ~400BC* Greek myths of Hephaestus and Pygmalion incorporated the idea of intelligent robots (such as Talos) and artificial beings (such as Galatea and Pandora). ~340BC* Aristotle described the syllogism, a method of formal, mechanical thought. ~100* Heron of Alexandria created mechanical men and other automatons. 1206* Ismael Al Jazari created a programmable orchestra of mechanical human beings (the book of knowledge of ingenious mechanical devices) 1580* Rabbi Judah Loew ben Bezalel of Prague is said to have invented the Golem, a clay man brought to life. 1642* Blaise Pascal invented the mechanical calculator, the first digital calculating machine. 1670* René Descartes proposed that bodies of animals are nothing more than complex machines Gottfried Leibniz improved the earlier machines, making the Stepped Reckoner to do multiplication and division. He also invented the binary numeral system and envisioned a universal calculus of reasoning. 1750

13 Julien Offray de La Mettrie published L'Homme Machine, which argued that human thought is strictly mechanical Wolfgang von Kempelen built and toured with his chess playing automaton, The Turk. The Turk was later shown to be a hoax, involving a human chess player. 1818* Mary Shelley published the story of Frankenstein; or the Modern Prometheus, a fictional consideration of the ethics of creating sentient beings George Boole set out to "investigate the fundamental laws of those operations of the mind by which reasoning is performed, to give expression to them in the symbolic language of a calculus", inventing Boolean algebra. 1863* Samuel Butler suggested that Darwinian evolution also applies to machines, and speculates that they will one day become conscious and eventually supplant humanity. 12

14 Artificial Intelligence, when? 1900s * Bertrand Russell and Alfred North Whitehead published Principia Mathematica, which revolutionized formal logic. 1923* Karel Čapek's play R.U.R. (Rossum's Universal Robots) opened in London. This is the first use of the word "robot" in English. 1931* Kurt Gödel showed that sufficiently powerful formal systems, if consistent, permit the formulation of true theorems that are unprovable by any theorem proving machine deriving all possible theorems from the axioms. To do this he had to build a universal, integer based programming language, which is the reason why he is sometimes called the "father of theoretical computer science". 1941* Konrad Zuse built the first working program controlled computers. 1943* Warren Sturgis McCulloch and Walter Pitts publish "A Logical Calculus of the Ideas Immanent in Nervous Activity" (1943), laying foundations for artificial neural networks. 1950* Alan Turing proposes the Turing Test as a measure of machine intelligence. 1950* Isaac Asimov published his Three Laws of Robotics and uses the term robotics and roboticist for the first time 1956 The first Dartmouth College summer AI conference is organized by John McCarthy, Marvin Minsky, Nathan Rochester of IBM and Claude Shannon. 1956* The name artificial intelligence is used for the first time as the topic of the second Dartmouth Conference, organized by John

15 McCarthy 1956 The first demonstration of the Logic Theorist (LT) written by Allen Newell, J.C. Shaw and Herbert A. Simon. This is often called the first AI program The General Problem Solver (GPS) demonstrated by Newell, Shaw and Simon John McCarthy and Marvin Minsky founded the MIT AI Lab. 1972* Shakey the Robot, the world's first robot capable of reasoning about its own actions 1978* Herbert Simon win the Nobel price in Economics for his theory of Bounded rationality, one of the AI cornerstones of AI known as Satisficing 1979* Hans Moravec builds Stanford Cart, the first autonomous vehicle 1979 Bill VanMelle's PhD dissertation at Stanford demonstrated the generality of MYCIN's representation of knowledge and style of reasoning (600 if then rules), the model for many commercial expert system "shells". 1980s Lisp machines developed and marketed. First expert system shells and commercial applications 1980s Neural Networks become widely used with the Backpropagation algorithm (first described by Paul Werbos in 1974) The team of Ernst Dickmanns at Bundeswehr University of Munich builds the first robot cars, driving up to 55 mph on empty streets AI takes off again, but with a focus on statistically learned low level capabilities rather than human engineered high level knowledge 1994 With passengers on board, the twin robot cars VaMP and VITA 2 of Ernst Dickmanns and Daimler Benz drive more than one thousand kilometers on a Paris three lane highway in standard heavy traffic at speeds up to 130 km/h. They demonstrate autonomous driving in free lanes, convoy driving, and lane changes left and right with autonomous passing of other cars. 1997* The Deep Blue chess machine (IBM) defeats the (then) world chess champion, Garry Kasparov First official RoboCup football (soccer) match featuring table top matches with 40 teams of interacting robots and over 5000 spectators. 13

16 1998* Tiger Electronics' Furby is released, and becomes the first successful attempt at producing a type of A.I to reach a domestic environment. 1999* Sony introduces an improved domestic robot similar to a Furby, the AIBO becomes one of the first artificially intelligent "pets" that is also autonomous. 13

17 Artificial Intelligence, when? 2000s YOU ARE HERE * Cynthia Breazeal at MIT publishes her dissertation on Sociable machines, describing Kismet (robot), with a face that expresses emotions. 2000* The Nomad robot explores remote regions of Antarctica looking for meteorite samples. 2002* irobot'sroomba autonomously vacuums the floor while navigating and avoiding obstacles DARPA introduces the DARPA Grand Challenge requiring competitors to produce autonomous vehicles for prize money. 2004* NASA's robotic exploration rovers Spirit and Opportunity autonomously navigate the surface of Mars. 2005* Honda's ASIMO robot, an artificially intelligent humanoid robot, is able to walk as fast as a human, delivering trays to customers in restaurant settings. 2005* Blue Brain is born, a project to simulate the brain at molecular detail Google builds its self driving car 2010 Microsoft launched Kinect for Xbox 360, the first device to track human body movements 2011* IBM's Watson computer defeated television game show Jeopardy! championsrutter and Jennings.

18 2011* Apple's Siri, Google's Google Now and Microsoft's Cortana are smartphone apps that use natural language to answer questions, make recommendations and perform actions. 2012* Voyager 1 crossed the heliopause and became the first robot to enter interstellar space 2012* Kiva Systems is the first robotics company to be sold for $775M. 2013* Robot HRP 2 built by SCHAFT Inc of Japan, a subsidiary of Google, defeats 15 teams to win DARPA s Robotics Challenge Trials An open letter to ban development and use of autonomous weapons signed by Hawking, Musk, Wozniak and 3,000 researchers in AI and robotics Google DeepMind's AlphaGo defeated 3 time European Go champion 2 dan professional Fan Hui by 5 games to * Libratus, designed by Carnegie Mellon professor Tuomas Sandholm and his grad student Noam Brown won against four top players at no limit Texas hold 'em, a very challenging version of poker 14

19 15 Artificial Intelligence, what? SECTION 03

20 ARTIFICIAL INTELLIGENCE

21 Artificial Intelligence, what? FOUR WAYS TO THINK OF AI THINKING HUMANLY THINKING RATIONALLY In the 1960s Cognitive revolution information-processing psychology replaced prevailing orthodoxy of behaviorism. [The automation of] activities that we associate with human thinking, activities such as decision-making, problem solving, learning BELLMAN, 1978 ACTING HUMANLY ACTING RATIONALLY The study of how to make computers do things at which, at the moment, people are better RICH & KNIGHT, 1991 The branch of Computer Science that is concerned with the automation of intelligent behavior LUGER & STUBBLEFIELD, 1993

22 Artificial Intelligence, what? THINKING HUMANLY: COGNITIVE SCIENCE AND NEUROSCIENCE In the 1960s, a Cognitive Revolution shifted an information-processing approach in psychology to a cognitive approach. The latest and most ambitious attempt: The Human Brain Project PROBLEM It requires information about the internal activity of the brain.

23 Artificial Intelligence, what? ACTING HUMANLY Published: Computing machinery and Intelligence (1950) Asked the question: Can machines think? Set an 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 the following 50 years ALAN MATHISON TURING (1951) Suggested major components of AI: knowledge, reasoning, language, understanding, learning June 9 th, 2014:

24 Artificial Intelligence, what? ACTING HUMANLY: THE IMITATION GAME 305 The standard interpretation of the Turing Test states that the interrogator, is given the task of trying to determine which player A or B is a computer and which is a human only using written questions/answers. In a more complete form of the test, also other AI sub-disciplines are used (i.e. Computer Vision, Natural Language Processing, etc). PROBLEM A Turing Test is not reproducible, constructive, or amenable to mathematical analysis. 20

25 ARTIFICIAL INTELLIGENCE

26 Artificial Intelligence, what? THINKING RATIONALLY: LAWS OF THOUGHT A set of norms or rules that guides the thinking process. This approach evolved out of mathematics and philosophy into modern AI. Aristotle was the first to formalize the concept of syllogism as consisting of three parts: major premise, minor premise, conclusion. No homework is fun Some reading is homework Some reading is not fun PROBLEM Not all intelligent behavior is mediated by logical deliberation. It also raises few questions, such as, what is the purpose of thinking? What thoughts should I have?

27 Artificial Intelligence, what? ACTING RATIONALLY A rational behavior is defined as: doing the right thing. The idea is to maximize the achievement of a goal given the available information. Acting rationally does not necessarily involve thinking, but thinking should be in the service of rational action. This approach makes use of agents, that is entities that perceive and acts. PROBLEM Everything Aristotle says is perfect! Aristotle said that. Therefore, that is perfect!

28 Every art and every inquiry, and similarly every action and pursuit, is thought to aim to some good; and for this reason the good has rightly been declared to be that at which all things aim. Aristotle

29 QUESTIONS? 25