Artificial Intelligence

Similar documents
Acting humanly: The Turing test. Artificial Intelligence. Thinking humanly: Cognitive Science. Outline. What is AI?

Artificial Intelligence

COMP 590: Artificial Intelligence

What is Artificial Intelligence?

CS440/ECE448: Artificial Intelligence. Course website:

Introduction to Artificial Intelligence

CSC384 Intro to Artificial Intelligence

Course Outline Department of Computing Science Faculty of Science. COMP Applied Artificial Intelligence (3,1,0) Fall 2015

COMP-424: Artificial intelligence. Lecture 1: Introduction to AI!

History of Artificial Intelligence. Introduction to Intelligent Systems

CSE 517A MACHINE LEARNING INTRODUCTION

Watson. An analytical computing system that specializes in natural human language and provides specific answers to complex questions at rapid speeds

Learning is a very general term denoting the way in which agents:

Vorlesung Grundlagen der Künstlichen Intelligenz

Applications of Artificial Intelligence. Omark Phatak

COMP-424: Artificial intelligence. Lecture 2: Introduction to AI!

CHAPTER 15: IS ARTIFICIAL INTELLIGENCE REAL?

Hyper-connectivity and Artificial Intelligence

Bowdoin Computer Science

Artificial Intelligence for ICT Innovation

Course 395: Machine Learning

EXECUTIVE SUPPORT SYSTEMS (ESS) STRATEGIC INFORMATION SYSTEM DESIGNED FOR UNSTRUCTURED DECISION MAKING THROUGH ADVANCED GRAPHICS AND COMMUNICATIONS *

Appendices master s degree programme Artificial Intelligence

2013 International Symposium on Green Manufacturing and Applications Honolulu, Hawaii

Game playing. Chapter 6. Chapter 6 1

CS Master Level Courses and Areas COURSE DESCRIPTIONS. CSCI 521 Real-Time Systems. CSCI 522 High Performance Computing

Lecture 1: Introduction to Reinforcement Learning

Fall 2012 Q530. Programming for Cognitive Science

ARTIFICIAL INTELLIGENCE: DEFINITION, TRENDS, TECHNIQUES, AND CASES

Web Data Mining: A Case Study. Abstract. Introduction

Computational Cognitive Science. Lecture 1: Introduction

Chess Algorithms Theory and Practice. Rune Djurhuus Chess Grandmaster / October 3, 2012

MAN VS. MACHINE. How IBM Built a Jeopardy! Champion x The Analytics Edge

An Introductory CS Course for Cognitive Science Students

21 st Century Knowledge Worker: the Centaur

Artificial Intelligence (AI)

A Client-Server Interactive Tool for Integrated Artificial Intelligence Curriculum

Game Playing in the Real World. Next time: Knowledge Representation Reading: Chapter

Artificial Intelligence I. Introduction: what s AI for? Homo Sapiens = Man the wise. Dr Mateja Jamnik. Computer Laboratory, Room FC18

THE DEVELOPMENT OF AN EXPERT CAR FAILURE DIAGNOSIS SYSTEM WITH BAYESIAN APPROACH

Introduction to Machine Learning and Data Mining. Prof. Dr. Igor Trajkovski

CSE841 Artificial Intelligence

Artificial Intelligence and Asymmetric Information Theory. Tshilidzi Marwala and Evan Hurwitz.

CS MidTerm Exam 4/1/2004 Name: KEY. Page Max Score Total 139

CSCI Historical Development. May 29, 2015

10. Machine Learning in Games

Chapter 11. Managing Knowledge

[CS9223] Game Design for Citizen Science

Levels of Analysis and ACT-R

Teaching Analy-cs, Big Data and Sustainability: An IS perspec-ve

Artificial Intelligence 2014

I N T E L L I G E N T S O L U T I O N S, I N C. DATA MINING IMPLEMENTING THE PARADIGM SHIFT IN ANALYSIS & MODELING OF THE OILFIELD

Artificial Intelligence and Politecnico di Milano. Presented by Matteo Matteucci

Cognitive Science. Summer 2013

New Predictive Analysis Solutions for Health Care

Computation Beyond Turing Machines

Theoretical Perspective

Study Plan for the Master Degree In Industrial Engineering / Management. (Thesis Track)

Putting IBM Watson to Work In Healthcare

Machine Learning Introduction

Measuring the Performance of an Agent

Computer Science Introduction

Watson Background September 2011 What does Watson mean to the insurance industry?

COGNITIVE SCIENCE 222

Master of Science in Artificial Intelligence

Computers and the Creative Process

Core Curriculum to the Course:

Government of Russian Federation. Faculty of Computer Science School of Data Analysis and Artificial Intelligence

Predicate logic Proofs Artificial intelligence. Predicate logic. SET07106 Mathematics for Software Engineering

CONTEMPORARY DECISION SUPPORT AND KNOWLEDGE MANAGEMENT TECHNOLOGIES

Research in the cognitive sciences is founded on the assumption

Chess Algorithms Theory and Practice. Rune Djurhuus Chess Grandmaster / September 23, 2014

Design and Development of Electronic Prescription and Patient Information Systems for Developing World By

Machine Learning. Chapter 18, 21. Some material adopted from notes by Chuck Dyer

ARTIFICIAL INTELLIGENCE METHODS IN EARLY MANUFACTURING TIME ESTIMATION

Programming Languages

How To Write A Computer Science Book

Neural Networks for Machine Learning. Lecture 13a The ups and downs of backpropagation

Lehrstuhl für Informatik 2

Managing Knowledge. Chapter 11 8/12/2015

Extinguished philosophies lie about the cradle of every science as the strangled snakes beside that of Hercules. - adapted from T. H.

Course Syllabus For Operations Management. Management Information Systems

Who needs humans to run computers? Role of Big Data and Analytics in running Tomorrow s Computers illustrated with Today s Examples

Appendices master s degree programme Human Machine Communication

IMPORTANCE OF QUANTITATIVE TECHNIQUES IN MANAGERIAL DECISIONS

UNIVERSALITY IS UBIQUITOUS

School of Computer Science

Using Artificial Intelligence to Manage Big Data for Litigation

Understanding Proactive vs. Reactive Methods for Fighting Spam. June 2003

Draft dpt for MEng Electronics and Computer Science

Likely Developments in ODR Notes Matthew Lavy and Richard Susskind July Introduction

Introduction to Artificial Intelligence

Artificial Intelligence

Data Quality in Information Integration and Business Intelligence

Circuits and Boolean Expressions

Artificial Intelligence academic programmes in the Netherlands. A state of the art report

John McCarthy Father of Artificial Intelligence

Schoo\ of Computing. Middlesbrough. Teesside University. 22 June To whom it may concern

playing smart artificial intelligence in computer games

Driving Insurance World through Science Murli D. Buluswar Chief Science Officer

Transcription:

Artificial Intelligence "

Artificial Intelligence" Lecturer: Phạm Bảo Sơn Email: sonpb@vnu.edu.vn Consultations: via email or after lecture. Course website: www.uet.vnu.edu.vn/~sonpb/ai AI 2016 2

Readings" Textbook: S. Russel and P. Norvig: Artificial Intelligence: A Modern Approach. Prentice-Hall, Second edition. Reference books: Ben Coppin: Artificial Intelligence Illuminated, Jones and Bartlett Publishers 2004. AI 2016 3

Course overview" Problem Solving using search techniques Blind search. Informed search Constraint satisfaction problem. Game Playing. Knowledge Representation: Propositional logic Predicate logic Reasoning mechanisms Probabilistic reasoning Prolog. Advanced Topics: Machine Learning e.g. decision tree, neural network Natural Language Processing AI 2016 4

C: Class mark: Assessment" Assignments Attendance and participation. E: Exam F: Final mark F = C*40% + E*60% AI 2016 5

Policy " Encourage discussion but assignments must be your individual work Codes copied from books or other libraries but be explicitly acknowledged Sharing or copying codes is strictly prohibited. AI 2016 6

Thermostat Chess Your car Google Asimo Vacuum cleaner AI Systems" AI 2016 7

What is AI?" The exciting new effort to make computers think machine with minds, in the full and literal sense. The study of mental faculties through the use of computational models The art of creating machines that perform functions that require intelligence when performed by people. AI is concerned with intelligent behaviour in artifacts. AI 2016 8

What is AI?" Views of AI fall into four categories: rationality vs. human (human are not perfect) acting vs. thinking Thinking humanlythinking rationally Acting humanly Acting rationally AI 2016 9

Thinking humanly: cognitive modeling" Requires scientific theories of internal activities of the brain Introspection Psychological experiments -- How to validate? Requires 1) Predicting and testing behavior of human subjects (topdown) or 2) Direct identification from neurological data (bottom-up) Both approaches (roughly, Cognitive Science and Cognitive Neuroscience) are now distinct from AI AI 2016 10

Acting humanly: Turing Test" Turing (1950) "Computing machinery and intelligence": "Can machines think?" à "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 Suggested major components of AI: knowledge, reasoning, language understanding, learning AI 2016 11

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: 1. Not all intelligent behavior is mediated by logical deliberation 2. What is the purpose of thinking? What thoughts should I have out of all the thoughts that I could have? AI 2016 12

Acting rationally" 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 AI 2016 13

Short History of AI " The Thinking Machine AI 2016 14

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 1950s Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine 1958 McCarthy invented LISP programming language. 1966 73 AI discovers computational complexity: scaling up prob. Neural network research almost disappears 1969 79 Early development of knowledge-based systems 1980-- AI becomes an industry 1986-- Neural networks return to popularity: back-propagation learning algorithm 1987-- AI becomes a science 1995-- The emergence of intelligent agents, statistical approaches 2000- Where are we now? AI 2016 15

State of the art" Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997. Deep Fritz defeated Kramnik in 2006. Watson defeated best human player in Jeopardy In 2011. 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 AI 2016 16

AI Systems Video demos" Watson is a Question answering (QA) computing system built by IBM. IBM describes it as "an application of advanced Natural Language Processing, Information Retrieval, Knowledge Representation and Reasoning, and Machine Learning technologies to the field of open domain question answering" which is "built on IBM's DeepQA technology for hypothesis generation, massive evidence gathering, analysis, and scoring. Google Self Driving Car Robocup VAV Virtual Assistant for Vietnamese - developed at FIT@UET AI 2016 17