Artificial Intelligence Notes
1. What is Artificial Intelligence?
Data: Raw facts, unformatted information.
Information: It is the result of processing, manipulating and organizing data in response to a
specific need. Information relates to the understanding of the problem domain.
Knowledge: It relates to the understanding of the solution domain – what to do?
Intelligence: It is the knowledge in operation towards the solution – how to do? How to apply
the solution?
Artificial Intelligence: Artificial intelligence is the study of how make computers to do things
which people do better at the moment. It refers to the intelligence controlled by a computer
machine.
One View of AI is
About designing systems that are as intelligent as humans
Computers can be acquired with abilities nearly equal to human intelligence
How system arrives at a conclusion or reasoning behind selection of actions
How system acts and performs not so much on reasoning process.
Why Artificial Intelligence?
Making mistakes on real-time can be costly and dangerous.
Time-constraints may limit the extent of learning in real world.
The AI Problem
There are some of the problems contained within AI.
1. Game Playing and theorem proving share the property that people who do them well
are considered to be displaying intelligence.
2. Another important foray into AI is focused on Commonsense Reasoning. It includes
reasoning about physical objects and their relationships to each other, as well as reasoning
about actions and other consequences.
3. To investigate this sort of reasoning Nowell Shaw and Simon built the General Problem
Solver (GPS) which they applied to several common sense tasks as well as the problem of
performing symbolic manipulations of logical expressions. But no attempt was made to
create a program with a large amount of knowledge about a particular problem domain.
Only quite simple tasks were selected.
4. The following are the figures showing some of the tasks that are the targets of work in AI:
K S V KRISHNA SRIKANTH, DEPT OF IT Page 1
,Artificial Intelligence Notes
Perception of the world around us is crucial to our survival. Animals with much less intelligence
than people are capable of more sophisticated visual perception. Perception tasks are difficult
because they involve analog signals. A person who knows how to perform tasks from several of
the categories shown in figure learns the necessary skills in standard order.
First perceptual, linguistic and commonsense skills are learned. Later expert skills such as
engineering, medicine or finance are acquired.
Physical Symbol System Hypothesis
At the heart of research in artificial intelligence, the underlying assumptions about intelligence lie
in what Newell and Simon (1976) call the physical symbol system hypothesis. They define a
physical symbol system as follows:
1. Symbols
2. Expressions
3. Symbol Structure
4. System
A physical symbol system consists of a set of entities called symbols, which are physically patters
that can occur as components of another type of entity called an expression (or symbol
structure). A symbol structure is composed of a number of instances (or tokens) of symbols
related in some physical way. At any instance of the time the system will contain a collection of
these symbol structures. The system also contains a collection of processes that operate on
expressions to produce other expressions: processes of creation, modification, reproduction and
destruction.
They state hypothesis as:
“A physical symbol system has the necessary and sufficient means for general
‘intelligent actions’.”
This hypothesis is only a hypothesis there appears to be no way to prove or disprove it on logical
ground so, it must be subjected to empirical validation we find that it is false. We may find the
bulk of the evidence says that it is true but only way to determine its truth is by experimentation ”
Computers provide the perfect medium for this experimentation since they can be programmed
to simulate physical symbol system we like. The importance of the physical symbol system
hypothesis is twofold. It is a significant theory of the nature of human intelligence and so is of
great interest to psychologists.
What is an AI Technique?
Artificial Intelligence problems span a very broad spectrum. They appear to have very little in
common except that they are hard. There are techniques that are appropriate for the solution of
a variety of these problems. The results of AI research tells that
Intelligence requires Knowledge. Knowledge possesses some less desirable properties
including:
It is voluminous
,Artificial Intelligence Notes
It is hard to characterize accurately
It is constantly changing
It differs from data by being organized in a way that corresponds to the ways it
will be used.
AI technique is a method that exploits knowledge that should be represented in such a
way that:
The knowledge captures generalizations. In other words, it is not necessary to
represent each individual situation. Instead situations that share important
properties are grouped together.
It can be understood by people who must provide it. Most of the knowledge a
program has must ultimately be provided by people in terms they understand.
It can be easily be modified to correct errors and to reflect changes in the world
and in our world view.
It can be used in a great many situations even if it is not totally accurate or
complete.
It can be used to help overcome its own sheer bulk by helping to narrow the
range of possibilities that must usually be considered.
It is possible to solve AI problems without using AI techniques. It is possible to apply AI
techniques to solutions of non-AI problems.
Important AI Techniques:
Search: Provides a way of solving problems for which no more direct approach is
available as well as a framework into which any direct techniques that are
available can be embedded.
Use of Knowledge: Provides a way of solving complex problems by exploiting the
structures of the objects that are involved.
Abstraction: Provides a way of separating important features and variations from
the many unimportant ones that would otherwise overwhelm any process.
Criteria for Success (Turing Test)
In 1950, Alan Turing proposed the method for determining whether a machine can think. His
method has since become known as the “Turing Test”. To conduct this test, we need two people
and the machine to be evaluated. Turing Test
provides a definition of intelligence in a machine
and compares the intelligent behavior of human
being with that of a computer.
One person A plays the role of the interrogator,
who is in a separate room from the computer and
the other person. The interrogator can ask set of
questions to both the computer Z and person X by
, Artificial Intelligence Notes
typing questions and receiving typed responses. The interrogator knows them only as Z and X
and aims to determine who the person is and who the machine is.
The goal of machine is to fool the interrogator into believing that it is the person. If the machine
succeeds we conclude that the machine can think. The machine is allowed to do whatever it can
do to fool the interrogator.
For example, if asked the question “How much is 12,324 times 73,981?” The machine
could wait several minutes and then respond with wrong answer.
The interrogator receives two sets of responses, but does not know which set comes from human
and which from computer. After careful examination of responses, if interrogator cannot
definitely tell which set has come from the computer and which from human, then the computer
has passed the Turing Test. The more serious issue is the amount of knowledge that a machine
would need to pass the Turing test.
Overview of Artificial Intelligence
It was the ability of electronic machines to store large amounts of information and process it at
very high speeds that gave researchers the vision of building systems which could emulate
(imitate) some human abilities.
We will see the introduction of the systems which equal or exceed human abilities and see them
because an important part of most business and government operations as well as our daily
activities.
Definition of AI: Artificial Intelligence is a branch of computer science concerned with the study
and creation of computer systems that exhibit some form of intelligence such as systems that learn
new concepts and tasks, systems that can understand a natural language or perceive and
comprehend a visual scene, or systems that perform other types of feats that require human types
of intelligence.
To understand AI, we should understand
Intelligence
Knowledge
Reasoning
Thought
Cognition: gaining knowledge by thought or perception learning
The definitions of AI vary along two main dimensions: thought process and reasoning and
behavior.
AI is not the study and creation of conventional computer systems. The study of the mind, the
body, and the languages as customarily found in the fields of psychology, physiology, cognitive
science, or linguistics.
In AI, the goal is to develop working computer systems that are truly capable of performing tasks
that require high levels of intelligence.
1. What is Artificial Intelligence?
Data: Raw facts, unformatted information.
Information: It is the result of processing, manipulating and organizing data in response to a
specific need. Information relates to the understanding of the problem domain.
Knowledge: It relates to the understanding of the solution domain – what to do?
Intelligence: It is the knowledge in operation towards the solution – how to do? How to apply
the solution?
Artificial Intelligence: Artificial intelligence is the study of how make computers to do things
which people do better at the moment. It refers to the intelligence controlled by a computer
machine.
One View of AI is
About designing systems that are as intelligent as humans
Computers can be acquired with abilities nearly equal to human intelligence
How system arrives at a conclusion or reasoning behind selection of actions
How system acts and performs not so much on reasoning process.
Why Artificial Intelligence?
Making mistakes on real-time can be costly and dangerous.
Time-constraints may limit the extent of learning in real world.
The AI Problem
There are some of the problems contained within AI.
1. Game Playing and theorem proving share the property that people who do them well
are considered to be displaying intelligence.
2. Another important foray into AI is focused on Commonsense Reasoning. It includes
reasoning about physical objects and their relationships to each other, as well as reasoning
about actions and other consequences.
3. To investigate this sort of reasoning Nowell Shaw and Simon built the General Problem
Solver (GPS) which they applied to several common sense tasks as well as the problem of
performing symbolic manipulations of logical expressions. But no attempt was made to
create a program with a large amount of knowledge about a particular problem domain.
Only quite simple tasks were selected.
4. The following are the figures showing some of the tasks that are the targets of work in AI:
K S V KRISHNA SRIKANTH, DEPT OF IT Page 1
,Artificial Intelligence Notes
Perception of the world around us is crucial to our survival. Animals with much less intelligence
than people are capable of more sophisticated visual perception. Perception tasks are difficult
because they involve analog signals. A person who knows how to perform tasks from several of
the categories shown in figure learns the necessary skills in standard order.
First perceptual, linguistic and commonsense skills are learned. Later expert skills such as
engineering, medicine or finance are acquired.
Physical Symbol System Hypothesis
At the heart of research in artificial intelligence, the underlying assumptions about intelligence lie
in what Newell and Simon (1976) call the physical symbol system hypothesis. They define a
physical symbol system as follows:
1. Symbols
2. Expressions
3. Symbol Structure
4. System
A physical symbol system consists of a set of entities called symbols, which are physically patters
that can occur as components of another type of entity called an expression (or symbol
structure). A symbol structure is composed of a number of instances (or tokens) of symbols
related in some physical way. At any instance of the time the system will contain a collection of
these symbol structures. The system also contains a collection of processes that operate on
expressions to produce other expressions: processes of creation, modification, reproduction and
destruction.
They state hypothesis as:
“A physical symbol system has the necessary and sufficient means for general
‘intelligent actions’.”
This hypothesis is only a hypothesis there appears to be no way to prove or disprove it on logical
ground so, it must be subjected to empirical validation we find that it is false. We may find the
bulk of the evidence says that it is true but only way to determine its truth is by experimentation ”
Computers provide the perfect medium for this experimentation since they can be programmed
to simulate physical symbol system we like. The importance of the physical symbol system
hypothesis is twofold. It is a significant theory of the nature of human intelligence and so is of
great interest to psychologists.
What is an AI Technique?
Artificial Intelligence problems span a very broad spectrum. They appear to have very little in
common except that they are hard. There are techniques that are appropriate for the solution of
a variety of these problems. The results of AI research tells that
Intelligence requires Knowledge. Knowledge possesses some less desirable properties
including:
It is voluminous
,Artificial Intelligence Notes
It is hard to characterize accurately
It is constantly changing
It differs from data by being organized in a way that corresponds to the ways it
will be used.
AI technique is a method that exploits knowledge that should be represented in such a
way that:
The knowledge captures generalizations. In other words, it is not necessary to
represent each individual situation. Instead situations that share important
properties are grouped together.
It can be understood by people who must provide it. Most of the knowledge a
program has must ultimately be provided by people in terms they understand.
It can be easily be modified to correct errors and to reflect changes in the world
and in our world view.
It can be used in a great many situations even if it is not totally accurate or
complete.
It can be used to help overcome its own sheer bulk by helping to narrow the
range of possibilities that must usually be considered.
It is possible to solve AI problems without using AI techniques. It is possible to apply AI
techniques to solutions of non-AI problems.
Important AI Techniques:
Search: Provides a way of solving problems for which no more direct approach is
available as well as a framework into which any direct techniques that are
available can be embedded.
Use of Knowledge: Provides a way of solving complex problems by exploiting the
structures of the objects that are involved.
Abstraction: Provides a way of separating important features and variations from
the many unimportant ones that would otherwise overwhelm any process.
Criteria for Success (Turing Test)
In 1950, Alan Turing proposed the method for determining whether a machine can think. His
method has since become known as the “Turing Test”. To conduct this test, we need two people
and the machine to be evaluated. Turing Test
provides a definition of intelligence in a machine
and compares the intelligent behavior of human
being with that of a computer.
One person A plays the role of the interrogator,
who is in a separate room from the computer and
the other person. The interrogator can ask set of
questions to both the computer Z and person X by
, Artificial Intelligence Notes
typing questions and receiving typed responses. The interrogator knows them only as Z and X
and aims to determine who the person is and who the machine is.
The goal of machine is to fool the interrogator into believing that it is the person. If the machine
succeeds we conclude that the machine can think. The machine is allowed to do whatever it can
do to fool the interrogator.
For example, if asked the question “How much is 12,324 times 73,981?” The machine
could wait several minutes and then respond with wrong answer.
The interrogator receives two sets of responses, but does not know which set comes from human
and which from computer. After careful examination of responses, if interrogator cannot
definitely tell which set has come from the computer and which from human, then the computer
has passed the Turing Test. The more serious issue is the amount of knowledge that a machine
would need to pass the Turing test.
Overview of Artificial Intelligence
It was the ability of electronic machines to store large amounts of information and process it at
very high speeds that gave researchers the vision of building systems which could emulate
(imitate) some human abilities.
We will see the introduction of the systems which equal or exceed human abilities and see them
because an important part of most business and government operations as well as our daily
activities.
Definition of AI: Artificial Intelligence is a branch of computer science concerned with the study
and creation of computer systems that exhibit some form of intelligence such as systems that learn
new concepts and tasks, systems that can understand a natural language or perceive and
comprehend a visual scene, or systems that perform other types of feats that require human types
of intelligence.
To understand AI, we should understand
Intelligence
Knowledge
Reasoning
Thought
Cognition: gaining knowledge by thought or perception learning
The definitions of AI vary along two main dimensions: thought process and reasoning and
behavior.
AI is not the study and creation of conventional computer systems. The study of the mind, the
body, and the languages as customarily found in the fields of psychology, physiology, cognitive
science, or linguistics.
In AI, the goal is to develop working computer systems that are truly capable of performing tasks
that require high levels of intelligence.
