You are on page 1of 35

Artificial Intelligence

Intelligence
This session
Previous session
Understood what is Artificial Intelligence
We shall discuss
What is Intelligence
What are agents
Overview of different methods to implement intelligence
At the end of the class, you should be able to
Understand the meaning
Agent
Intelligence,
Know the different categories of artificial intelligence
What is Artificial Intelligence ?
Artificial Intelligence is the synthesis and
analysis of computational agents that act
intelligently
An agent is something that acts in an
environment.
Eg,
Dog, cat, worm, Robot, Human
AGENT
We should be interested in
what an agent does;
how it acts;
And judge the agent by its actions

An agent acts intelligently if:


its actions are appropriate for its goals and circumstances
it is flexible to changing environments and goals
it learns from experience
it makes appropriate choices given perceptual and
computational limitations
Computational agent
A computational agent is an agent whose decisions about
its actions can be explained in terms of computation.
That is, the decision can be broken down into primitive
operation that can be implemented in a physical
device.
This computation can take many forms.
In humans this computation is carried out in Brain";
in computers it is carried out in "hardware."
open question
whether all intelligent agents are computational ?.
Open Question ?

Differentiate between Natural And Artificial


Intelligence
Artificial and Natural Intelligence
Artificial intelligence" is a source of much confusion because artificial
intelligence may be interpreted as the opposite of real intelligence.

Natural means occurring in nature and artificial means made by people.

A tsunami is a large wave in an ocean caused by an earthquake or a landslide.


Natural tsunamis occur from time to time. You could imagine an artificial tsunami
that was made by people, for example, by exploding a bomb in the ocean, yet
which is still a real tsunami. One could also imagine fake tsunamis: either artificial,
using computer graphics, or natural, for example, a mirage that looks like a
tsunami but is not one.

If an agent behaves intelligently, it is intelligent. It is only the external


behavior that defines intelligence; acting intelligently is being intelligent.
Thus, artificial intelligence, if and when it is achieved, will be real
intelligence created artificially
Goals of Artificial Intelligence
Scientific goal:
to understand the principles that make intelligent behavior
possible in natural or artificial systems.
analyze natural and artificial agents
formulate and test hypotheses about what it takes to construct
intelligent agents
design, build, and experiment with computational systems that
perform tasks that require intelligence
Engineering goal:
design useful, intelligent artifacts.

Analogy between studying flying machines and thinking


machines.
Sources of human intelligence
Humans are helpless at birth but evolve into an intelligent Agent
Human intelligence comes from three main sources:
biology:
Humans have evolved into adaptable animals that can survive in
various habitats.
culture:
Culture provides not only language, but also useful tools, useful
concepts, and the wisdom that is passed from parents and
teachers to children.
life-long learning:
Humans learn throughout their life and accumulate knowledge
and skills.
Open Question ?
For each of the following, give five reasons why:
A dog is more intelligent than a worm.
A human is more intelligent than a dog.
An organization is more intelligent than an
individual human.
Based on your observation, give a definition of
what "more intelligent" may mean.
Collective Intelligence

Each individual ant may not be very intelligent


but an ant colony can act more intelligently
than any individual ant.
The colony can
discover food
exploit it very effectively
adapt to changing circumstances.
Collective Intelligence
Modern computers, from low-level hardware to
high-level software, are more complicated for any
human to understand, yet they are manufactured
daily by organizations of humans
One class of intelligent agents that may be more
intelligent than humans is the class of
organizations.
Human society viewed as an agent is arguably the
most intelligent agent known
Agents in an environment
Agents
At any time an agent depends on its
Abilities:-
which are the primitive actions it is capable of carrying
out.
Prior knowledge:-
about the agent and the environment;
History :-
History of interaction with the environment, which is
composed of
observations of the current environment and
past experiences of previous actions and observations, or
other data, from which it can learn;
Goals that it must try to achieve or preferences over states of
the world; and
Examples of Agents
Examples of Agents

Organizations
Microsoft, Al Qaeda, Government of India , Wipro,...
People
Teachers, physicians, stock traders, engineers, researchers,
travel agents, farmers, waiters...
Computers/devices
Thermostats, user interfaces, airplane controllers, network
controllers, games, advising systems, tutoring systems,
diagnostic assistants, robots, Google car, Mars rover...
Animals
Dogs, mice, birds, insects, worms, bacteria.
Inputs to an agent
Abilities :-
The set of things it can do
Goals/Preferences:-
What it wants, its desires, its values,...
Prior Knowledge:-
What it comes into being knowing,
What it doesn't get from experience,...
History :-
Observations (percepts, stimuli) of the environment
Current observations :- what it observes now
Past experiences :- what it has observed in the past
Example agent: Teacher
Abilities :-
Present new concept, drill, give test, explain concept,. .
Goals/Preferences:-
Impart particular knowledge, skills, inquisitiveness,
social skills,. . .
Prior Knowledge:-
Subject material, teaching strategies,. . .
History observation:-
Test results, facial expressions, errors, focus,. . .
Past experiences :-
Prior test results, effects of teaching strategies, . . .
Example agent: Robot
Abilities :-
movement, grippers, speech, facial expressions,. . .
Goals/Preferences:-
deliver food, rescue people, score goals, explore,. . .
Prior Knowledge:-
what is important feature, categories of objects, what a
sensor tell us,. . .
History observation:-
vision, sonar, sound, speech recognition, gesture
recognition,. . .
Past experiences :-
effect of steering, slipperiness, how people move,. . .
Example agent: Medical Doctor
Abilities :-
____________________________________________.
Goals/Preferences:-
____________________________________________.
Prior Knowledge:-
____________________________________________.
History observation:-
____________________________________________.
Past experiences :-
____________________________________________.
Example agent: Autonomous Car
Abilities :-
____________________________________________.
Goals/Preferences:-
____________________________________________.
Prior Knowledge:-
____________________________________________.
History observation:-
____________________________________________.
Past experiences :-
____________________________________________.
Example agent: Wipro Ltd.
Abilities :-
____________________________________________.
Goals/Preferences:-
____________________________________________.
Prior Knowledge:-
____________________________________________.
History observation:-
____________________________________________.
Past experiences :-
____________________________________________.
Programming AI
Methods and techniques
Methods
Storing information
Facts
Rules
Retrieving Information
Searching
Pattern Matching
Techniques
Algorithms
Heuristics
Intelligent Systems
Artificial Intelligence
Knowledge Representation
Extracting information
Reasoning
General categories of AI
Expert Systems
Fuzzy Systems
Neural Networks
Genetic Algorithms
Intelligent Systems Characteristics
Any system to be termed as intelligent is should
possess these characteristics(at least a subset)

Characteristics
Logical behavior
Ability to solve complex problems
Responsive and adaptive nature
Means to effectively use existing information
User friendliness and highly interactive
Reliability
Intelligent Systems
Computers and Programs
Computers
Multiple processor systems
Capable of receiving and processing real-time signals
Sometimes specialized equipment
Specialized semantics
Programs
Ability to
Use knowledge to perform certain tasks and solve problems
Exploit powers of association to infer and solve real world
problems
Handle vagueness in problem
Solve complex optimization problems using search techniques
Expert Systems
Uses
knowledge, inference procedures
Solves
difficult problems requiring human expertise
Expert Systems
Fuzzy Systems
Fuzzy
form of many-valued logic
deals with approximate, rather than exact reasoning.

Fuzzy logic has been extended to handle the


concept of partial truth
fuzzy logic variables may have a truth value that
ranges in degree between 0 and 1.
where the truth value may range between completely
true and completely false.
Fuzzy Systems
Neural Networks
neural networks are models inspired by biological
neural networks ( brain)
Artificial neural network is a system of interconnected
"neurons" which send messages to each other.
Used to estimate or approximate functions that can
depend on a large number of inputs and are generally
unknown.
The connections between neurons have numeric
weights that can be tuned based on experience
neural nets adaptive to inputs and capable of learning.
Neural Networks
Genetic algorithm
Genetic algorithm
mimics the process of natural selection
(nature)
search heuristic that is routinely used to
generate useful solutions to
Optimization
search problems
Swarm intelligence
Swarm intelligence
is the collective behavior of decentralized, self-organized
systems, natural or artificial
There is no centralized control structure dictating how
individual agents should behave
The agents follow
very simple rules
Local
random to a certain degree

interactions between agents "intelligent" global behavior


intelligence is unknown to the individual agents.
Genetic algorithm
Intelligent Systems - Domains

Expert Genetic Swarm


Application Fuzzy System Neural System
System System Intelligence

Diagnosis

Optimization

Problems

Predictions

Control

Applications