csnb234 artificial intelligence
DESCRIPTION
CSNB234 ARTIFICIAL INTELLIGENCE. Chapter: Part I Background & History of AI. Natural Vs. Artificial intelligence. What is Natural Intelligence? Human intelligence The word ‘natural’ is normally omitted What is Artificial Intelligence? Intelligences posses by machines What is IQ?. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/1.jpg)
COIT, UNITEN
CSNB234ARTIFICIAL INTELLIGENCE
Chapter: Part IBackground & History of AI
Chapter: Part IBackground & History of AI
![Page 2: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/2.jpg)
COIT, UNITEN 2
Natural Vs. Artificialintelligence
What is Natural Intelligence? Human intelligence The word ‘natural’ is normally omitted
What is Artificial Intelligence? Intelligences posses by machines
What is IQ?
![Page 3: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/3.jpg)
COIT, UNITEN 3
IQ of a personis measured by
Mental AgeIQ = -------------------------------- * 100 Chronological Age
Mental AgeIQ = -------------------------------- * 100 Chronological Age
E.g. if a 20 years old person undergoes an IQ test and the examiner determines his mental age as 18, then his IQ is 90 ------------------> below average!
This is the simplest formula that works well
![Page 4: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/4.jpg)
COIT, UNITEN 4
AI can be defined as the attempt to get real
machines to behave like the ones in the movies.
First glance at the definition of AI
![Page 5: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/5.jpg)
COIT, UNITEN 5
AI programs Vs. Traditional programs
Traditional Program =____________ + ____________
AI Program = _____________ + _____________
Main difference Heuristics vs. Algorithmic
Traditional Program =____________ + ____________
AI Program = _____________ + _____________
Main difference Heuristics vs. Algorithmic
![Page 6: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/6.jpg)
COIT, UNITEN 6
The AI Theorists
Father of “Artificial Intelligence is Alan Turing
Other AI Theorists: McDermott, Patrick Winston, Newell,
Simon, Rosenblatt& more (perform an internet
search)..
![Page 7: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/7.jpg)
COIT, UNITEN 7
Warren McCulloch (Columbia University) Human Brain
Claude Shannon (Bell Lab)Boolean Algebra
Norbert Wiener John McCarthy (Dartmouth College) Marvin Minsky (Harvard U)
![Page 8: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/8.jpg)
COIT, UNITEN 8
Alan Turing(1912-1954)
He is the father of AI
![Page 9: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/9.jpg)
COIT, UNITEN 9
AI : History 1956: Dartmouth Conference - proposed launch of Joint
Research on AI. John McCarthy, Marvin Minsky, Claude Shannon among the
attendees.
1960s: Focus on knowledge bases started. Areas of interests are chess games, theorem proving and language translation. Lisp developed by John McCarthy.
1963: Newell & Simon built General Problem Solver (GPS).
1965: DENDRAL developed by Feigenbaum at Stanford University.
![Page 10: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/10.jpg)
COIT, UNITEN 10
1970s: MYCIN developed at Stanford University, utilised production rules.
1972: PROLOG developed by Alain Colmerauer at University of Marseilles.
1981: ICOT (Institute of New Generation Computer Technology).
![Page 11: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/11.jpg)
COIT, UNITEN 11
Symbolic Processing
It is a branch of Computer Science that deals with symbolic, non-algorithmic methods of problem solving.
Heuristics
It is the branch of Computer Science that deals with ways of representing knowledge using symbols rather than numbers and with rules-of-thumb for processing information.
![Page 12: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/12.jpg)
COIT, UNITEN 12
Heuristics and Heuristic programming
Heuristics– Developed through intuition, experience & judgment.– Do not represent (our) knowledge of design, rather,
they represent guidelines through which a system may be operated.
– Often called “Rules of thumb”.
Characteristics Screening Filtering Pruning
![Page 13: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/13.jpg)
COIT, UNITEN 13
HEURISTIC PROGRAMMING
• Should not be confused with computer programming.
• A program is a solution; programming is a procedure for obtaining a solution.
• Thus, heuristic programming is a procedure for finding the solution to a model consisting of “heuristics”.
![Page 14: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/14.jpg)
COIT, UNITEN 14
LANGUAGE LEVELS FOR AI PROBLEM SOLVING
Two Levels of Abstraction: Symbol level Knowledge level
Symbol Level:– concerns with the particular formalisms used to
represent knowledge such as logic or production rules.
– concerns with the structures used to organize knowledge.
![Page 15: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/15.jpg)
COIT, UNITEN 15
Knowledge Level:
What queries / questions will be asked? How new knowledge can be added or
updated? What objects and relations are
necessary? Can the system reasons despite of
incompleteness of information?
![Page 16: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/16.jpg)
COIT, UNITEN 16
Essential requirements for an AI language
Support of Symbolic Computation– implementation of a set of operation on
symbolic rather than numeric data.
– predicate calculus is a powerful tool for constructing qualitative descriptions of a domain.
![Page 17: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/17.jpg)
COIT, UNITEN 17
Flexibility of Control– Rule-based systems being the most
important paradigm for building AI programs.
– AI cannot be achieved through step-by-step execution of a fixed sequence of instructions .
– Production rules can be fired in virtually any order (i.e. not step-by-step) in response to a given situation.
![Page 18: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/18.jpg)
COIT, UNITEN 18
Support of Exploratory Programming Methodologies– AI programs seldom respond to standard
software approaches such as top-down design, stepwise refinement.
– This is due to the nature of AI problems that they could be started & tested without having to completely produce the final specification.
– In other words, most AI programs are initially poorly specified.
– AI programming is inherently exploratory; the program is the vehicle through which we explore the problem area (domain) and discover solution strategies.
Support of Exploratory Programming Methodologies– AI programs seldom respond to standard
software approaches such as top-down design, stepwise refinement.
– This is due to the nature of AI problems that they could be started & tested without having to completely produce the final specification.
– In other words, most AI programs are initially poorly specified.
– AI programming is inherently exploratory; the program is the vehicle through which we explore the problem area (domain) and discover solution strategies.
![Page 19: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/19.jpg)
COIT, UNITEN 19
Late Binding & Constraint Propagation
– Often, the problems addressed by AI program (such as Prolog program) require that the values of certain entities to remain unknown until sufficient information is gathered to determine the assignment.
– As constraints are accumulated, the set of possible values is reduced, ultimately converging on a solution.
![Page 20: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/20.jpg)
COIT, UNITEN 20
Clear and Well-defined Semantics– Traditional computer languages are too
complex in its programming constructs and semantic definitions. They are not subject to self-proof.
– This could be achieved by developing new languages that do not (to certain extent) conform to the architecture underlying von Neumann computer and be on the foundation of mathematical formalisms such as logic (Prolog).
Clear and Well-defined Semantics– Traditional computer languages are too
complex in its programming constructs and semantic definitions. They are not subject to self-proof.
– This could be achieved by developing new languages that do not (to certain extent) conform to the architecture underlying von Neumann computer and be on the foundation of mathematical formalisms such as logic (Prolog).
![Page 21: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/21.jpg)
COIT, UNITEN 21
AI Systems Development
Knowledge and expertise slowly building up..
Immature but can be used (tested)
This methodology is called _____________
![Page 22: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/22.jpg)
COIT, UNITEN 22
CCSB354ARTIFICIAL INTELLIGENCE
Chapter 1: Part IIIntroduction to AI
Chapter 1: Part IIIntroduction to AI
![Page 23: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/23.jpg)
COIT, UNITEN 23
Can a machine think?
Can be answered by the following “tests” for machine (i.e. the program/software)
The Alan Turing Test Alan Turing (father of AI)
Revised Turing Test ELIZA (By Joseph Weizenbaum of MIT)
![Page 24: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/24.jpg)
COIT, UNITEN 24
Artificial Intelligence
Definition AI is the study of how to make computers do things at
which, at the moment, people are better. What computer can do better than people?
Numerical computation: Fast & accurate Information storage: Voluminous amounts Repetitive operations : Not getting bored (??)
However, these are mechanical mindless activities, and thus cannot be regarded as ‘intelligent’ tasks
![Page 25: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/25.jpg)
COIT, UNITEN 25
What people can do better than computers?
Activities that involve intelligence include: Understanding Common sense reasoning Natural language processing and generation Planning & Design Learning (e.g. from mistakes, by analogy, by
experience or examples) Emotions
![Page 26: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/26.jpg)
COIT, UNITEN 26
What is “intelligence”?
It has the ability To respond to situation very flexibly To make sense out of ambiguous messages To recognize the relative importance of different
elements of a situation
It is the part of Computer Science that concerned with the designing of intelligent computer systems, that is, systems that exhibit characteristics we associate with intelligence
in human behavior.
![Page 27: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/27.jpg)
COIT, UNITEN 27
Differences between AI and Conventional Systems
Conventional SystemsProceduralNumerical
processingAlgorithmicRigid syntax
AI Systems
Declarative Symbolic processing Heuristic
programming More natural syntax
![Page 28: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/28.jpg)
COIT, UNITEN 28
Areas of AI Research Automated reasoning Expert systems Natural language processing Speech recognition Computer vision Robotics Automatic programming Data mining Optimization
![Page 29: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/29.jpg)
COIT, UNITEN 29
Applied Fields of AIApplied Fields of AI
ExpertSystems
NaturalLanguageProcessing
RoboticsComputer
Vision
ComputerizedSpeech
RecognitionMachineLearning
AI
![Page 30: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/30.jpg)
COIT, UNITEN 30
Other AI branches:
1.Intelligent software agents2.Machine learning3.Neural networks4.Evolutionary algorithms5.Semantic technology
![Page 31: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/31.jpg)
COIT, UNITEN 31
Class Exercise 1
Some characteristics of “intelligence” are: Be able to identify d_________ between situations. Be able to identify w______________ in a situation. Be able to respond to a situation very f________. Be able to l____ from experience. Be able to p__________ and make events cohere. Be able to see s__________ out of complexity. Be able to ad______, j ______, and j________. Be able to handle un___________ of information/data.
Some characteristics of “intelligence” are: Be able to identify d_________ between situations. Be able to identify w______________ in a situation. Be able to respond to a situation very f________. Be able to l____ from experience. Be able to p__________ and make events cohere. Be able to see s__________ out of complexity. Be able to ad______, j ______, and j________. Be able to handle un___________ of information/data.
![Page 32: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/32.jpg)
COIT, UNITEN 32
Class Exercise 2
Name some features of “Artificial Intelligence”.
The use of large amount of d________- s________ knowledge in its problem solving.
Solutions may be just g____- e________ (i.e. neither exact nor optimal).
Q_______ and S________ aspects are in concern (not numerical analysis).
Non-a____________. H_________ programming is the key to software
intelligence.
Name some features of “Artificial Intelligence”.
The use of large amount of d________- s________ knowledge in its problem solving.
Solutions may be just g____- e________ (i.e. neither exact nor optimal).
Q_______ and S________ aspects are in concern (not numerical analysis).
Non-a____________. H_________ programming is the key to software
intelligence.
![Page 33: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/33.jpg)
COIT, UNITEN 33
The Birth of AI (I)
The Turing TestThis test was invented by Alan Turing (1912-
1954) It was first described in his 1950 article Computing
machinery and intelligence (Mind, Vol. 59, No. 236, pp. 433-460)
An interrogator is connected to one person and one machine via a terminal, and therefore can't see his counterparts.
![Page 34: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/34.jpg)
COIT, UNITEN 34
The Birth of AI (II) The Turing Test
His task is to find out which of the two candidates is the machine, and which is human only by asking them questions.
If the interrogator cannot make a decision within a certain time (Turing proposed five minutes, but the exact amount of time is generally considered irrelevant),
the machine is considered to be intelligent.
![Page 35: CSNB234 ARTIFICIAL INTELLIGENCE](https://reader036.vdocument.in/reader036/viewer/2022062807/56814fd5550346895dbd97e9/html5/thumbnails/35.jpg)
COIT, UNITEN 35
If the computer succeeds in fooling the interrogator, i.e. the interrogator cannot distinguish the machine from the human,then, Turing argues, the machine may be assumed to be “intelligent”
Siapa yang menjawab ini?
Pening aku ni...