Artificial Intelligence

Rakesh Kumar Bachchan

CDCSIT, T.U.
 Introduction
At the beginning of the stone age, when people started taking
shelter in caves they made attempt to immortalise themselves by
painting their images on rocks.

With the gradual progress of civilisation, they felt interested to

see themselves in different forms. So they started constructing
models of human being with sand, clay and stones.

They are not satisfied by only this thing.

Human being had a strong desire to make the model intelligent

so that it could act and think as he did. Which was definitely a
complex task.

The first significant success in the modern era of computing is

the Charles Babbage analytical engine.
 Introduction Contd…
The second generation computers comes shortly after the invention of
Transistor. They were mainly used for commercial data processing and
payroll creation.

After more than a decade, IC were produced and Third generation

computers are introduced that can perform massive computation in real
time.

Then after a decade The fourth generation computer with VLSI were
developed. Many electronics robots were developed during this period.

During 1980 -1990 Japanese government started to produce Fifth

Generation computing machines that have all the capabilities of the fourth
generation computer and also able to process intelligence.

They can process natural language, play games, recognise images of object
and prove mathematical theorems, all of which lies in the domain of AI. So
What is AI?
 Artificial Intelligence
Artificial Intelligence??

Intelligence: Ability to acquire and apply knowledge and skills.

Artificial Intellience:

Branch of computer science concerned with the automation of

intelligence

The study of computation that make it possible to perceive, reason

and act.

The study of mental faculties through the use of computational

models.

Simulation of human intelligence in machine, so as to make the

machine efficient to identify and use the right piece of
knowledge at a given step of solving problem.
 Artificial Intelligence
Contd…

From Russel & Norvig

Top dimension is concerned with thought process and reasoning, Where the bottom dimension addresses the
behaviour.

Definiton on the left measures success in terms of fidelity of human performance

Definition on the right measures an ideal concept of intelligence which is called rationality
Artificial Intelligence
Contd…
Acting Humanly: The Turing Test Approach

Thinking Humanly: The Cognitive Modelling

Approach

Thinking Rationally: The “Laws Of Thought”

Approach

Acting Rationally: The Rational Agent

Approach
 Acting Humanly: The
Turing Test Approach
Turing Test

Total Turing Test: includes video signals and

manipulation capability so that the interrogator
can test the subject‘s perceptual abilities and
object manipulation ability. To pass the total
Turing test computer must have following
additional capabilities:

Robotics: To manipulate objects and move

Computer Vision: To perceive objects

 Thinking Humanly: The
Cognitive Modelling Approach
How human thinks?

we need to get inside the actual working of

human minds. There are two ways to do so:

1. Through inspection: trying to catch our own

thought as they go by

2. Through psychological experiments: once we

have precise theory of mind, it becomes
possible to express the theory as a computer
program.
 Think Rationally: The
“Laws of thought” Approach
Syllogisms: form of logical reasoning consisting of three proposition. e.g.

“Ram is a man; all men are mortal; therefore, Socrates is mortal.”

These laws of thought were supposed to govern the operation of the

mind; their study initiated the field of logic.

The logistic tradition within AI hopes to build on programs to create

intelligent systems.

Two main obstacles to this approach:

1. It is not easy to take informal knowledge and state it in

formally as required by logic.

2. There is big difference between solving a problem in principle

than in practice.
 Acting Rationally: The
Rational Agent Approach
Agent: is something that acts

Rational Agent: is something that acts so as to achieve the best

outcome or, when there is uncertainty the best expected
outcome.

In the laws of thought approach, emphasis was on correct

inferences

Making correct inference is sometimes part of being rational

agent, because one way to act rationally is to reason logically.

Some ways of acting rationally may not involve inference. e.g.

Recoiling from a hot stove is a reflex action.
 Foundations of AI
Philosophy

Mathematics

Economics

Neuroscience

Psychology

Computer Engineering

Control Theory and Cybernetics

Linguistics
 History of AI
The Gestation of Artificial Intelligence

The birth of Artificial Intelligence (1956)

Early enthusiasm, great expectations

A dose of reality

Knowledge based systems: the key to power?

AI becomes an industry

The return of neural networks

AI becomes a science

The emergent of Intelligent agents

 Applications of AI
Autonomous planning and scheduling

Game playing

Autonomous Control

Diagnosis

Logistics Planning

robotics

Language understanding and problem solving

 AI Problems
Common Place Problems (these are done by all people routinely)

Recognizing people

Communicating (Through natural language)

Navigating around obstacles on the streets

Expert tasks (That cannot be done by all people) Include

Medical Diagnosis

Mathematical problem solving

playing game like chess

 Practical
implementation
Embedded in numerous devices e.g. in copy machines for automatic correction of operation for
copy quality improvement

credit card fraud detection

speech recognition, etc…

Some Famous AI System

ALVINN (Autonomous Land Vehicle in a Neural Network)

Developed by Dean Pomerleau

Learns to control vehicle by watching human drive

Deep Blue

Developed by IBM

A chess playing computer that defeated Gary Kasparov

Machine Translation

System capable of translating languages between people speaking different languages.

Thanks