Introduction to Artificial Intelligence, Lecture notes of Artificial Intelligence

Download Introduction to Artificial Intelligence and more Lecture notes Artificial Intelligence in PDF only on Docsity! Introduction to Artificial Intelligence Outline I. What is AI? II. A brief history III. The state of the art * Some of the notes are adapted from those by Dr. Jin Tian. I. What Is Intelligence? A wish-list of general characteristics of intelligence • Perception: manipulation & interpretation of data provided by sensors I. What Is Intelligence? A wish-list of general characteristics of intelligence • Perception: manipulation & interpretation of data provided by sensors • Action: control and use of effectors to accomplish a variety of tasks • Reasoning: deductive (logical) inference, inductive inference • Learning: adapting behavior to better cope with changing environments, discovery of patterns, learning to reason, plan, and act. I. What Is Intelligence? A wish-list of general characteristics of intelligence • Perception: manipulation & interpretation of data provided by sensors • Action: control and use of effectors to accomplish a variety of tasks • Reasoning: deductive (logical) inference, inductive inference • Learning: adapting behavior to better cope with changing environments, discovery of patterns, learning to reason, plan, and act. • Communication: with other intelligent agents including humans using signals, signs, icons, … I. What Is Intelligence? A wish-list of general characteristics of intelligence • Perception: manipulation & interpretation of data provided by sensors • Action: control and use of effectors to accomplish a variety of tasks • Reasoning: deductive (logical) inference, inductive inference • Learning: adapting behavior to better cope with changing environments, discovery of patterns, learning to reason, plan, and act. • Communication: with other intelligent agents including humans using signals, signs, icons, … • Planning: formulation of plans -- sequences or agenda of actions to accomplish externally or internally determined goals Acting Humanly: Turing Test Alan Turing (1950) : operational definition of intelligence * Illustration art from https://wsimag.com/science-and-technology/36961-no-turing-test-for-consciousness. • A human interrogator poses some written questions to another human and a computer (or “robot”). • The computer passes the test if the interrogator cannot tell whether the written responses come from the human responder or the computer. Human interrogatorHuman respondent Robot Annual Loebner prize competition (since 1990): the first prize of $100,000 to be awarded to the first program that passes the "unrestricted" Turing test. Six Disciplines of AI Natural language processing to communicate in a human language; Knowledge representation to store what it knows; Automated reasoning to answer questions and draw new conclusions; Machine learning to adapt to new circumstances and to detect patterns. To pass the Turing test, the following capabilities are required: Six Disciplines of AI Natural language processing to communicate in a human language; Knowledge representation to store what it knows; Automated reasoning to answer questions and draw new conclusions; Machine learning to adapt to new circumstances and to detect patterns. Total Turing test requires interaction with the real world. Computer vision & speech recognition to perceive the world; Robotics to move around in the world and to manipulate objects. To pass the Turing test, the following capabilities are required: Thinking Humanly: Cognitive Modeling To say a program thinks like a human, we must know humans think first. Learn about human thought in three ways: • introspection – catching thoughts as they go by; • psychological experiments – observing a person in action; • brain imaging – observing brain activities. General problem solver (GPS) by Newell & Simon (1961) Cognitive science constructs theories of the human mind by combining  computer models from AI  experimental techniques from psychology Also compares reasoning steps to those in the human solution. Thinking Rationally: “Laws of Thought” Represent problems using logic and build programs to create intelligent systems. Drawbacks:  Not easy to state informal (and often uncertain) knowledge in the formal logical notation.  Big difference between solving a problem “in principle” and solving it in practices. Acting Rationally: Rational Agent This course is about designing rational agents. Rational behavior: doing the right thing expected to maximize goal achievement, given the available information • An agent is an entity that perceives and acts. • A rational agent is one that acts to achieve the best outcome. Brief History of AI (cont’d) • 1969-86 Expert systems • 1980- AI becomes an industry: expert systems booms, then busts (1988-93): AI Winter” • 1986- Neural networks regain popularity • 1987- Probabilistic reasoning and machine learning Brief History of AI (cont’d) • 1995- Emergence of intelligent agents  AI technologies continue to find applications in  information retrieval  data mining and knowledge discovery  customizable software systems  bioinformatics  autonomous vehicles  agile manufacturing systems  smart devices (e.g., home, automobiles)  …  internet tools: search engines, recommender systems  Steady progress on fundamental AI research problems continues. Brief History of AI (cont’d) • 2001- Big data  Successful large-scale real-world applications in  image recognition  natural language processing  speech recognition  machine translation • 2011- Deep learning  …  Convolutional neural networks (CNNs) e.g., ImageNet Turing Award Winners in AI 1969 Marvin Minsky (MIT) 1971 John McCarthy (Stanford) National Medal of Science (1990) 1975 Allen Newell* (Carnegie Mellon) National Medal of Science (1992) Herbert Simon* (Carnegie Mellon) Nobel Prize in Economics (1978) National Medal of Science (1986) 1994 Edward Feigenbaum (Stanford) Raj Reddy (Carnegie Mellon) 2011 Judea Pearl (UCLA) 2018 Yoshua Bengio (U Montreal) Geoffrey Hinton (U Toronto) Yann Lecun (NYU & Facebook) *omitted by the textbook on p. 17. Big mistake! Founders of AI Academic Genealogy Herbert Simon Allen Newell Edward Feigenbaum Raj Reddy John McCarthy * All the photos are from https://amturing.acm.org/byyear.cfm. Marvin Minsky Albert Tucker Solomon Lefschetz III. The State of the Art  Deep Blue (IBM) defeated the reigning world chess champion Garry Kasparov (1997).  Chinook defeated human checkers champions (1994). • Game playing  Supercomputer Watson (IBM) beat human champions on “Jeopardy” (2011).  AlphaGo (Google) beat the world’s No.1 ranking player Ke Jie in Go (2017).  Libratus (Carnegie Mellon) defeated the world’s best Texas Hold ‘em poker players head-to-head (2017), six-player (2019).  “AlphaStar” AI (Google) defeated human pros at StarCraft II (2019) (cont’d) • Robotic vehicles  Stanley (Stanford) won the DARPA Grand Challenge (2005)  Boss (Carnegie Mellon) won the DARPA’s Urban Challenge (2007) • Legged robots (Boston Dynamics)  Self-driving cars by Tesla, Google, etc. Stanley Boss Google car Tesla car crash Florida, 2016 AtlasSpotMini (cont’d) • Robotic vehicles  Stanley (Stanford) won the DARPA Grand Challenge (2005)  Boss (Carnegie Mellon) won the DARPA’s Urban Challenge (2007) • Legged robots (Boston Dynamics)  Self-driving cars by Tesla, Google, etc. Stanley Boss Google car Tesla car crash Florida, 2016 AtlasSpotMini Handle (cont’d) • Autonomous planning  NASA’s Remote Agent program controlled the scheduling of operations for a space craft (2000).  Uber and Google Maps plan optimal routes for hundreds of millions of users. • Speech recognition  Flight booking via conversation with an automated system  Real-time speech-to-speech translation • Image understanding  ImageNet object recognition  Image captioning Extensive use of convolutional neural networks (CNNs)