Scribd
Upload
52 views22 pages

AI Lecture 1

The document discusses artificial intelligence, including its history and major areas of application. It covers expert systems, knowledge representation, problem solving techniques like search and inference, and applications such as robotics, natural language processing, computer vision, and speech recognition. The document also discusses what intelligence is, different views of AI, and the Turing test for evaluating machine intelligence.

Uploaded by

Mstafa Mhamad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
52 views22 pages

AI Lecture 1

The document discusses artificial intelligence, including its history and major areas of application. It covers expert systems, knowledge representation, problem solving techniques like search and inference, and applications such as robotics, natural language processing, computer vision, and speech recognition. The document also discusses what intelligence is, different views of AI, and the Turing test for evaluating machine intelligence.

Uploaded by

Mstafa Mhamad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 22

Artificial Intelligence :

1) Charniak, E. & McDermott, D. 1985


Introduction to Artificial Intelligence
Reading, Massachusetts: Addison – Wesley
2) Rich, E. 1983.
Artificial Intelligence,
New York: McGrew – Hill
3) Winston, P. H. 1984.
Artificial Intelligence (2nd Edition)
Reading, Massachusetts: Addison – Wesley
4) Artificial Intelligence & the Design of Expert Systems
By: George F. Luger & William A. stubblefield 2009
Expert Systems:
1) Introduction To Expert Systems
F. Hayes – Roth
Addison

2) Expert Systems Techniques & Applications


P. Jackson
Addison
• AI is the study of Mental faculties through the
use of Computational models.

• AI is the part of Computer Science concerned with


designing intelligent Computers System, that is,
systems that exhibit the characteristics we associate
with intelligence in human behavior:- Learning,
Reasoning, Solving Problems,….
AI & The World
AI Researches are trying to create a computer
which think
AI applications :-
Robotics
Natural language processing
Vision
Speech
Expert systems
-6-
What is AI about?
AI is getting computers to do things that seem to
be intelligent

“INTELLIGENCE” is a vague word

AI not well defined field

Advanced sw engineering (sophisticated sw


techniques for hard problems that CAN’T be
solved in an easy way) .
Non – numeric ways of solving problems .
AI is concerned with programming computers
to perform tasks that are presently done by
human.
AI goal:-
To build a person or an animal

Fundamental assumption

What the brain does may be thought of at some


level as a kind of computation
AI includes getting computer to :
Communicating in Natural Language (NLP)

Remember complicated interrelated fact, and draw


conclusion from them (Inference)

Plan sequence of action to accomplish goals (Planning)

Offer advice based on complicated rules (ES)

Look through cameras & see what’s there (Vision)

Move objects (Robotics)


Why AI is not a science ?
AI does not quite fit in with other categories of science.

Most area of AI do not develop in the way that a


mathematical area traditional develops.

Ai does not fit in the general model of a physical science.

In AI we are almost never in the business of finding theories


or descriptions for existing physical phenomena which are
identical by experiment, or using experiments to look in
nature for phenomena which those theories or descriptions
predict.
AI can be distinguished from other sciences in that it
refers to objects (Programs or conceptual structures
capable of being realized in programs) which are created
by humans rather than objects having a prior natural
existence.

AI can be viewed as a technology

Deals with created objects


Mental Faculties

INPUT INTERNALS OUTPUT

IR IR
Vision Robotics
Deduction &
Search
planning
Explanation
IR Learning IR
Language Speech

IR : Internal Representation
Major Application area
Fundamental concerns
 Knowledge Represents : Addresses the problem of capture the full
range of knowledge required for intelligent behavior formal
language.
 Search : Is a problem – solving techniques that systematically
explore a space of problem state.
1) Game playing (board game)
 Well – defined set of rules.
 Easy representation of board
 Generate extremely large search spaces (heuristics)
2) Automated Reasoning and Theorem proving.
Representing the problem description and relevant
background information as logical axioms and treating
problem instances as theorems to be proved.
3) Expert Systems
Problems – solving in a domain – specific knowledge.
Expert knowledge in a combination of :
 Theoretical understanding of the problem
 A Collection of heuristic problem – solving rule
(DENDRAL , MYCIN , PROSPECTOR , INTERNIST , XCON ).

-14-
example:
• R1/XCON - configured VAX computer systems on the
basis of customers' needs. McDermott, 1980.

• PROSPECTOR - interpreted geological data as potential evidence


for mineral deposits. Duda, Hart, et al 1976.

• MYCIN - diagnosed blood infection. Shortliffe, 1976.

• INTERNIST - medical expert systems

• DENDRAL - advised the user on how to interpret the


output from a mass spectrograph

• MACSYMA -advised the user on how to solve complex


maths problems.
4) Natural language understanding : creation of computer that are
capable of understanding human language.
5) Planning robotics.
Planning assumes a robot that is capable of performing certain
atomic action , It attempts to find a sequence of those action that
will accomplish some higher – level tasks such as moving across
an obstacle – filled room.
6) Machine Learning.
Unlike a human being , expert , if it’s given the same or similar
problems a second time , it will not remember the solution. It
performs the same sequence of computation again.
THE AI SCIENTIFIC ISSUES
What are the central scientific issues of AI field from Which this more applied
research draws it’s inspiration?
1) Knowledge Representation : How shall the knowledge of the field be
represented as data structure in the memory of the computer , so that they
can be conveniently accessed for problem – solving?

1) Knowledge utilization : How can this knowledge be used in problems –


solving ? What design for the inference engine are available ?

3) Knowledge acquisition : How is it possible to acquire the knowledge so


important for problems – solving automatically .
AI is a part of computer science

AI is a part of computer science Based on theoretical and


applied principles that field:

Data structure used in knowledge representation


Algorithms needed to apply that knowledge
Language and programming techniques used in there
implementation
The problem of defining A.I. becomes one of defining intelligence itself.

1) Is Intelligence a single faculty , or is just a name for a collection of distinct


unrelated abilities?
2) To what extent is intelligence learned as apposed to having an a priori
existence?
3) What does happen when learning occurs?
4) What is creativity ? Intuition ?
5) Can Intelligence be inferred from observable behavior , or does it require
evidence of particular internal mechanism ?
6) How is knowledge represented in nerve tissue of living being, and what
lessons does this have for the design of intelligence machines ?
7) Is it even possible to achieve intelligence on a computer , or does an
intelligent entity require the richness of sensation and experience that might
be found only in a biological existence?
• All these unanswered questions have helped to shape the problems
and solution methodologies that constitute the core of modern A.I.

• Different interpretations have been used by different researchers as


defining the scope and view of Artificial Intelligence.

1. One view is that artificial intelligence is about designing systems


that are as intelligent as humans. This view involves trying to
understand human thought and an effort to build machines that
emulate the human thought process. This view is the cognitive science
approach to AI.

2.The second approach is best come to life by the concept of the


Turing Test. Turing held that in future computers can be programmed
to acquire abilities equaling human intelligence.
Turing Test

Consider There are two rooms, A and B. One of the rooms


contains a computer. The other contains a human.

The interrogator is outside and does not know which one is a


computer. He can ask questions through a teletype and
receives answers from both A and B.

The interrogator needs to identify whether A or B are


humans. To pass the Turing test, the machine has to fool
the interrogator into believing that it is human
The turning test

1) The turning test measures the performance of an allegedly


intelligent machine against that human being.
2) The intelligence to distinguish the computer from the human
being interrogator.
3) Comparing machine performance on a given set of problems
to that of a human expert.
3. Logic and laws of thought deals with studies of ideal or
rational thought process and inference.

The emphasis in this case is on the inferencing mechanism,


and its properties.

That is how the system arrives at a conclusion, or the


reasoning behind its selection of actions is very important
in this point of view.

You might also like