Download Artificial Intelligence 人工智能

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Person of Interest (TV series) wikipedia , lookup

Human-Computer Interaction Institute wikipedia , lookup

Machine learning wikipedia , lookup

Wizard of Oz experiment wikipedia , lookup

Artificial intelligence in video games wikipedia , lookup

Computer Go wikipedia , lookup

Technological singularity wikipedia , lookup

Expert system wikipedia , lookup

Computer vision wikipedia , lookup

Knowledge representation and reasoning wikipedia , lookup

Embodied cognitive science wikipedia , lookup

Intelligence explosion wikipedia , lookup

Ethics of artificial intelligence wikipedia , lookup

Existential risk from artificial general intelligence wikipedia , lookup

AI winter wikipedia , lookup

Philosophy of artificial intelligence wikipedia , lookup

History of artificial intelligence wikipedia , lookup

Transcript
Artificial Intelligence
人工智能
Xiu-jun GONG (Ph. D)
School of Computer Science and Technology, Tianjin
University
[email protected]
http://cs.tju.edu.cn/faculties/gongxj/course/ai/
About the instructor


Name: Xiu-jun GONG (宫秀军)
Work experiences
2006/05-Now: Associate Professor, Tianjin University
 2003/05-2006/03: Research fellow, Nara Institute of Science
and Technology
 2003/02-2003/05: Visiting fellow, Institute for Inforcomm
Research (I2R), Singapore
 2002/07-2002/12: Research fellow, National University of
Singapore
 1999/09-2002/07: Ph. D candidate, Institute of Computing,
CAS
Research interests
 Data mining: algorithms, standards, and systems
 Bioinformatics: gene regulatory network, SNP identifications
 Medical informatics: secure, privacy-preserving data mining,
medical data integration and sharing framework


About the course

Text book




Grading





Artificial Intelligence-A New Synthesis, Nils J. Nillson
Artificial Intelligence: A Modern Approach, Stuart Russell
and Peter Norvig
Artificial Intelligence: Structures and Strategies for
Complex Problems Solving (Fourth Edition), George F.
Luger
Attendance: 10%
Project & Assignment: 20%
Final exam: 70%
Office hour: any time upon pre-appointment
before final exam, 25-B-1208
Web site: http://cs.tju.edu.cn/~gongxj/course/ai
Outline to the introduction
AI definitions
 AI history
 AI research
 Problems
 Approaches
 Tools
 AI Applications
 AI resources

What is AI
To make computers think ...
machines
with
minds
(Haugeland, 1985)
The study of the computations
that make it possible to perceive,
reason … (Winston,1992)
Machines that perform
The automation of intelligent
functions that require
behavior
intelligence when performed
by people (Kurzweil, 1990) (Luger, 1993)
Thinking humanly
Thinking rationally
Acting
Acting
humanly
rationally
What is AI (cont.)

AI is a branch of cs that is concerned with the
automation of intelligent behavior—Luger


What is the “intelligent behavior”?



Data structures, algorithms, and language and
programming techniques.
Think (act) humanly
Think (act) rationally
Can machines think?



Can: Now or someday; theoretically or actually
Machine: biological body (made of proteins), mechanical
device?
Think: media? Living cells or physical symbolic systems
Some synonyms
Intelligent machine, intelligent system, intelligent agent,
computational intelligence, synthetic intelligence
Performed by google trends on 7th, Oct, 2008
Beyond the definitions



The definitions differ for different people, different
contexts, and different historical periods (see the
AI history)
AI has always been more concerned with
expanding the capacities of computer science
than with defining its limits
AI is the interdisciplinary study of computer
science including psychology, philosophy,
neuroscience, cognitive science, linguistics,
ontology, operations research, economics, control
theory, probability, optimization and logic.
Collection of problems and methodologies
studied by AI researchers
History of AI research
Precursors
 1943−1956: The birth of AI
 1956−1974: The golden years
 1974−1980: The first AI winter
 1980–1987: Boom
 1987−1993: Bust: the second AI winter
 1993−present: AI ?

Precursors (1)

AI in myth, fiction and speculation
Precursors (2)
Al-Jazari's programmable
automata
Automatons
Computer science
Formal reasoning
1943−1956: The birth of AI (2)

Turing's test (1950) -ACT Humanly

Decide whether a machine is intelligent or not
If a machine could carry on a conversation (over a teletype) that
was indistinguishable from a conversation with a human being,
then the machine could be called "intelligent."
1943−1956: The birth of AI (2)

Dartmouth Summer
Research Conference on
Artificial Intelligence in
1956


Marvin Minsky, John
McCarthy
Coined the term “AI”


Every aspect of learning or
any other feature of
intelligence can be so
precisely described that a
machine can be made to
simulate it --a clear
statement of the
philosophical position of AI
research
Presentation of game playing
programs and Logic Theorist.
1956−1974: The golden years (1)

Reasoning as search



Maze problem--backtracking
Combinatorial explosion-- heuristics or "rules
of thumb “
Projects




Simon etc, General Problem Solver (1951)
Herbert Gelernter , Geometry Theorem Prover (1958)
James Slagle, SAINT (Symbolic Automatic
Integrator )(1961)
Nils Nilsson , STRIPS(Stanford Research Institute
Problem Solver ) (1971)
1956−1974: The golden years (2)

Natural language





Allow computers to communicate in natural languages-semantic network
STUDENT, solve high school algebra word problems
(1964)
ELIZA, rephrasing many of the patient's statements as
questions and posing them to the patients (1966)
ALICE: http://www.alicebot.org
Micro-worlds
Marvin Minsky, machine vision
They pointed out that in successful sciences were often
best understood using simplified models like frictionless
planes or perfectly rigid bodies. Much of the research
focused on the so-called "blocks world," which consists
of colored blocks of various shapes and sizes arrayed on
a flat surface .

1974−1980: The first AI winter (1)

Critiques from across campus (mainly from
philosophers )




John Lucas, argued Gödel's incompleteness theorem (a formal
system could never see the truth of certain statements, while
a human being could)
Hubert Dreyfus, argued that human reasoning actually
involved very little "symbol processing" and a great deal of
embodied, instinctive, unconscious "know how".
John Searle‘, Chinese Room argument (a program could not be
said to "understand" the symbols that it uses )
Perceptrons and the dark age of connectionism


perceptron may eventually be able to learn, make
decisions, and translate languages (Frank Rosenblatt,
1958)
Minsky and Papert's, book Perceptrons. 1969
1974−1980: The first AI winter (2)

The neats: logic, Prolog and expert systems





Logic into AI: McCathy 1958
Deduction on computers: J. Alan Robinson 1963
Prolog: Philippe Roussel, Alain Colmerauer, 1972
Critics: human beings rarely used logic when they
solved problems
The scruffies: frames and scripts


Gerald Sussman observed that "using precise language
to describe essentially imprecise concepts doesn't make
them any more precise."
Minsky noted that many of his fellow "scruffy"
researchers were using the same kind of tool: a
framework that captures all our common sense
assumptions about something. 1975
1980–1987: Boom (1)

The rise of expert systems (main stream of
AI)



MYCIN, 1972, diagnosed infectious blood diseases
XCON (eXpert CONfigurer), 1980, automatically
selecting the computer system components based on
the customer's requirements
The knowledge revolution


The power of expert systems came from the expert
knowledge they contained
Cyc (enCyclopedia), assemble a comprehensive ontology
and database of everyday common sense knowledg,
Douglas Lenat 1984
1980–1987: Boom (2)

The revival of connectionism



John Hopfield (associative neural
network ,1982)
David Rumelhart (backpropagation)
The money returns

the fifth generation project ($850
million,1982, 10-year program)





“epoch-making computer”
massive parallel processing
Failure in 1992
Alvey (England, ₤350 )(1983-1987) PIM/m-1 machine
Strategic Computing Initiative (DARPA)
(1984)
1987−1993: the second AI winter

Market changed


Desktop computers from Apple and IBM had been
steadily gaining speed and power
Robotics facts—having a body essentially



A machine needs to have a body — it needs to perceive,
move, survive and deal with the world
David Marr, AI needed to understand the physical
machinery of vision from the bottom up before any
symbolic processing took place.
Rodney Brooks, Elephants Don't Play Chess , symbols
are not always necessary since "the world is its own best
model”. “physical symbol system hypothesis”
1993−present: AI ?







Deep Blue beats Kasparov (1997)
DARPA grand challenge: Autonomous vehicle
navigates across desert. (Urban Challenge next)
2005
NASA Remote Agent in Deep Space I probe
explores solar system
iRobot Roomba automated vacuum cleaner
Automated speech/language systems for airline
travel
Usable machine translation thru Google
…?
Advanced Intelligence

Close interactions and coordination
between Natural Intelligence and Artificial
Intelligence

The frontiers in both Artificial Intelligence
and Natural Intelligence

Large-scale Distributed Intelligence and
Web Intelligence
China’ s Programs on AI

国家中长期科学和技术发展规划纲要(2006-2020)
 重点领域及其优先主题
传感器网络及智能信息处理
重点开发多种新型传感器及先进条码自动识别、射频标签、基于多种传
感信息的智能化信息处理技术,发展低成本的传感器网络和实时信息
处理系统,提供更方便、功能更强大的信息服务平台和环境。


基础研究:
脑科学与认知科学
主要研究方究向:脑功能的细胞和分子机理,脑重大疾病的发生发
展机理,脑发育、可塑性与人类智力的关系,学习记忆和思维等
脑高级认知功能的过程及其神经基础,脑信息表达与脑式信息处
理系统,人脑与计算机对话等。

Problems of AI










Deduction, reasoning, problem solving
Knowledge representation
Planning
Learning
Natural language processing
Motion and manipulation
Perception
Social intelligence
Creativity
General intelligence
Approaches to AI
Thinking humanly
Thinking rationally
The cognitive
approach
The laws of
thought approach
Acting humanly
Acting rationally
The Turing Test
approach
The rational agent
approach
Approaches to AI cont.

Symbolism




Connectionism – Hopfield, Pitts


Cognitive simulation: Psychologism- Herbert
Simon and Alan Newell)
Logical AI: Logicism - John McCarthy
"Scruffy" symbolic AI : Computerism,
commonsense knowledge bases - Marvin
Minsky
Neural networks
Actionism – Brooks

Cybernetics and brain simulation
Tools of AI research
Search and optimization
 Logic
 Probabilistic methods for uncertain
reasoning
 Classifiers and statistical learning
methods
 Neural networks
 Control theory

Specialized languages
Lisp is a practical mathematical notation
for computer programs based on lambda
calculus
 Prolog is a declarative language where
programs are expressed in terms of
relations, and execution occurs by running
queries over these relations
 STRIPS a language for expressing
automated planning problem instances.
 Planner is a hybrid between procedural
and logical languages.

Application domains
Machine Learning
 Natural Language Processing
 Expert System
 Patten Recognition
 Computer Vision
 Robotics
 Game Playing
 Automatic Theorem Proving
 Automatic Programming

机器学习
自然语言处理
专家系统
模式识别
计算机视觉
机器人学
博弈
自动定理证明
自动程序设计
Application domains (cont. )
智能控制
Intelligent Control
 Intelligent Decision Support 智能决策支持系
统
System
人工神经网络
 Artificial Neural Network
 Knowledge Discovery in
知识发现和数据
Database & Data Mining
挖掘
 Distributed AI
分布式人工智能
 Intelligent Agent
智能代理
 Intelligent Retrieval from
智能数据库检索
Database

AI resources: Journals (premium)










Artificial Intelligence
Computational Linguistics
IEEE Trans on Pattern Analysis and Machine Intl
IEEE Trans on Robotics and Automation
IEEE Trans on Image Processing
Journal of AI Research
Neural Computation
Machine Learning
Intl Jnl of Computer Vision
IEEE Trans on Neural Networks
AI resources: Journals (leading)

















Artificial Intelligence Review
ACM Transactions on Asian Language Information Processing
AI Magazine
Applied Artificial Intelligence
Artificial Intelligence in Medicine
Computational Intelligence
Computer Speech and Language
Expert Systems with Applications: An Intl Jnl
IEEE Trans on Systems, Man, & Cybernetics, Part A & B
Intl Jnl on Artificial Intelligence Tools
Jnl of Experimental & Theoretical AI
Journal of East Asian Linguistics
Knowledge Engineering Review
Machine Translation
Neural Networks
Pattern Recognition
Neurocomputing
AI competitions

Machine Intelligence Prize

Loebner prize

KDD Cup serires
AI resources: Conferences











AAAI: American Association for AI National Conference
CVPR: IEEE Conf on Comp Vision and Pattern Recognition
IJCAI: Intl Joint Conf on AI
ICCV: Intl Conf on Computer Vision
ICML: Intl Conf on Machine Learning
KDD: Knowledge Discovery and Data Mining
KR: Intl Conf on Principles of KR & Reasoning
NIPS: Neural Information Processing Systems
UAI: Conference on Uncertainty in AI
AAMAS: Intl Conf on Autonomous Agents and Multi-Agent
Systems
ACL: Annual Meeting of the ACL (Association of
Computational Linguistics)
Summary

AI definition


AI history


Whatever the definition is, Collection of
problems and methodologies studied by AI
researchers is an important clue for
investigating AI problems
History is a mirror. AI researchers are getting
more intelligent
AI research

Integration of multi-disciplines.
Bring AI into practice and reality