Anda di halaman 1dari 37

What is AI Foundation of AI History of AI State of the Art of AI (applications)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

Artificial?

not genuine made by human and do not occur by nature


Ability to perform reasoning Ability to acquire knowledge Ability to apply knowledge (sense) Ability to perceive and manipulate things (understand)

Intelligent?

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

There is no agreed definition of the term Artificial Intelligence (AI). However, there are various definitions that have been proposed.

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

10

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

11

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

12

Discipline that automates reasoning processes to create machines that:


Thinking humanly Acting humanly Thinking rationally Acting rationally

Goal create computer systems that perform tasks regarded as requiring intelligence when done by humans.
CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009) 13

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

14

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

15

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

16

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

17

AI methodology
Based on application to be developed, such as Expert System (ES) software & hardware
Knowledge representation Search method Rule based Reasoning logic, uncertainty Agents

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

18

Example of intelligent action What to buy at the mall? A birthday present for a friend What present do I buy? What reason to buy? How could a computer achieve this task? Try to figure what basic AI processes would be involved in the following :

Translating English sentences into Malay Teaching a child to subtract integers Solving a crossword puzzle
CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009) 19

Alan Turing's 1950 article Computing Machinery and Intelligence discussed conditions for considering a machine to be intelligent Can machines think?Can machines behave intelligently? The Turing test (The Imitation Game): Operational definition of intelligence.

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

20

The Turing Test just consists of a machine behaving as a human impersonator. If the machine can fool humans into thinking it is human, then the machine is considered intelligent.

Basically the Turing Test is like the old saying, "if something looks like a duck, quacks like a duck, and walks like a duck (and tastes like duck), then it's a duck".
CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009) 21

Turing treats the computer and the human brain as "black boxes". He is not interested in the inner workings, only the outward performance.

He provides a scientific, empirical, performance test by which to judge the success of the AI project.
CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009) 22

Behavioral approach to determine whether or not a system is intelligent Proposed by Alan Turing (1950) Conversation key to judge intelligence Measures the performance of an allegedly intelligent machine against that of a human being (the best and standard for intelligent behavior) Called Imitation Game Place machine and human counterpart apart from second human being (interrogator) Interrogator not able to see or speak directly does not know which entity is machine Communicate by textual device (terminal)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

23

Distinguish the machine from human base on their answer to questions asked over terminal device If can not distinguish the machine may be assumed to be intelligent Interrogator need to uncover the machines identity may ask arithmetic calculation assume machine will be more likely to get it correct than human. So the machine need to know when they should fail in order to seem like human

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

24

Important outcomes/results/features:
Give understanding or idea or belief of intelligence i.e. the behavior to response to a particular set of questions. Prevent from being sidetracked by such confusing and currently unanswerable question as whether or not the computer uses the appropriate internal processes. Eliminates any bias forcing interrogator to focus solely on the content of the answers to the questions.

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

25

1. The Dark Age: Birth of Artificial Intelligence (1943-1956 2. The Rise of Artificial Intelligence great expectation (1956 late 1960s) 3. Unfulfilled promises impact of reality (late 1960s early 1970s) 4. The technology of expert system key to success (early 1970s mid 1980s) 5. How to make machine learn rebirth of neural networks (mid 1980s onwards) 6. Evolutionary Computation learning by doing (early 1970s onwards) 7. The new era of knowledge Engineering computing with words ( late 1980s onwards)
CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

26

1943 McCulloch & Pitts: Boolean circuit model of brain 1950 Turings Computing Machinery and Intelligence 1950s Early AI programs, including Samuels checkers program, Newell & Simons Logic Theorist, Gelernters Geometry Engine 1656 Dartmouth meeting: Artificial Intelligence adopted 1965 Robinsons complete algorithm for logical reasoning 1966-74 AI discovers computational complexity , Neural network research almost disappears 1969-79 Early development of knowledge-based systems 1980-88 Expert systems industry booms 1988-93 Expert systems industry busts: AI Winter 1985-95 Neural networks return to popularity 1988 Resurgence of probability: general increase in technical depth Nouvelle AI:ALife, GAs, soft computing 1995 Agents, agents, agentseverywhere 2003 Human-level AI back on the agenda
CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009) 27

Game playing
IBMs Deep Blue First AI to beat a human chess champion : Garry Kasparov, 1997 Blondie24 Machine learning program that won a checkers tournament Commercial game AI Increase in more sophisticated AI work for nonacademic games

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

28

Logistics Planning
Trip itineraries Engines such as MapQuest use AI to propose driving directions from one location to another Dynamic Analysis and replaning Tool (DART) Used during the 1991 Persian Gulf crisis to assist in managing military resources (over 50,000 people, vehicles and cargo shipments) Airline flight scheduling If flights are delayed or re-routed, AI planners are used to figure the best way to re-schedule departures and arrivals
CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009) 29

Speech recognition
Airline reservation systems Often robust to many different voice pitches and accents Automatic transcription Monitor language and content for live radio and television Assist in the transcribing of closed-captioned television programs

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

30

Text processing
Automated language translation Altavistas Babelfish server Information retrieval Google search engine Text classification and organization Google news, SPAM filtering Document summarization Columbia Universitys Newsblaster

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

31

Biology & Medicine


Diagnosis systems Specialists often use statistical AI tolls to diagnose a patient has a disease based in his/her symptoms Genome analysis software Now that the human and other genomes are complete. AI is used to identify new genes, infer biochemical pathways, and compare genomes of multiple species

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

32

Vision
Handwriting recognition US Postal Service automatically sorts mail Face recognition Government/bank security systems Autonomous Land Vehicle In a Neural Network (ALVINN) Uses camera data to automatically steer a car on a highway at speeds up to 65 mph (from Washington, DC to San Diego and back)

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

33

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

34

A computer program with problem solvers situated in interactive environments, which are each capable of flexible, autonomous, yet socially organized actions that can be. Criteria Explanation
Receives input from environment in which it is active and can also effect changes within that environment
Interact with environment without direct intervention of other agents. Responsive and proactive depending on its current situation. Interact with other software, oriented towards the goal.

Example
ROBOCUP (soccer player) interact with ball and opponent without full knowledge of locations, challenges, etc.
Pass the ball to teammate or on goal depending on its individual situation. Move the ball depending to opponent pattern. To score a goal interact with each other.

Situatedness

Autonomous

Flexible

Social

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

35

Most intelligent solutions require a variety of agents (society) Including Rote agents capture and communicate pieces of information Coordination agents support the interactions between other agents Search agents examine multiple pieces of information and return some bit of it Learning agents examine collections of information and form concepts or generalizations Decision agents dispatch tasks and come to conclusions in the light of limited information and processing

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

36

Main requisites for design and build such society Structures for the representation of information Strategies for the search through alternative solutions The creation of architectures that can support the interaction of agents

CSC463-Fundamentals of AI (UiTM Trg MP Jul 2009)

37