Introduction of AI

and its Applications

Module -I

Programme: B. Tech(IT 6th Sem)

Course Code: Artificial Intelligence
(CSE401)
Faculty: Dr. Seema Rawat
 Assessment/ Examination Scheme
Theory L/T (%) Lab/Practical/Studio (%)

80% 20%
Continuous Assessment/Internal Assessment End Term
(40%) Examination
(60 %)
Viva/Case
Study/
Minor
Components Attendance Assignment Project Quiz
(Drop down) Class Test Group presentation

3 10 3
Linkage of PSDA
with Internal
Assessment
Component, if any
Weightage (%) 5 15 4 60
 Assessment/ Examination Scheme

Continuous Assessment/Internal End Term

Assessment Examination
(60
(40 %) %)

Components (Drop
down Lab record Performance Viva Attendance Practical Viva Total
Performa
nce

Weightage (%) 10 15 10 5 30 30 60
 Index

Introduction to Artificial Intelligence

Applications
• Games
• Vision and speech processing
• Natural language processing
• Robotics
• Expert systems
• Theorem proving
 Learning Objective

To gain the knowledge about general AI techniques that have

been useful in many applications

5
 Learning Outcomes

• Basic understanding of the building blocks of AI

• Fundamental knowledge to understand what the AI is

• Information about the basic principles and applications

of Artificial Intelligence
Artificial + Intelligence

7
“Everything we love about civilization
is a product of intelligence, so
amplifying our human intelligence
with artificial intelligence has the
potential of helping civilization
flourish like never before – as long as
we manage to keep the technology
beneficial.“ - Max Tegmark

8
 Artificial Intelligence

The Encyclopedia Britannica states,

“artificial intelligence (AI), the ability of
a digital computer or computer-
controlled robot to perform tasks
commonly associated with intelligent
beings.”
 Artificial Intelligence

Merriam-Webster defines artificial intelligence this way [1] :

• A branch of computer science dealing with the simulation of
intelligent behavior in computers.
• The capability of a machine to imitate intelligent human behavior.
 Artificial Intelligence

According to John McCarthy, who is known as the father of AI,

• “AI is the science and engineering of making intelligent

machines, especially computer programs.”

11
 Some more Definitions

Artificial Intelligence

“Artificial intelligence (AI) is the intelligence exhibited by machines or

software” [2].

“The study and design of intelligent agents, where an intelligent agent is

a system that perceives its environment and takes actions that
maximize its chances of success” [3]
 AI: Why?

Computers are basically well suited to perform the mechanical

computations by using fixed programmed rules. This allows
machines to perform simple monotonous tasks efficiently and
reliably in which, humans are much efficient.
 AI
History
• Up-to early 80’s: Creation of expert systems (systems specialized for one
particular task based on experts’ knowledge), wide industry adoption

Modern AI
• Towards more scientific, formal/mathematical
• Divided into many subareas interested in particular aspects
• More directly connected to “neighboring” disciplines
• Theoretical computer science, statistics,, operations research, biology,
economics, psychology, neuroscience etc
Motivation

Examples of each of these

fields?

Ans:
Tic-Tac-Toe,
Remote Surgery,
E-Learning and many more
Human vs AI

16
 Identify this famous activity.
Ans: Turing Test

 To which AI philosophy, you

can relate turing test?

a. Think Humanly
b. Think Rationally
c. Act Humanly
d. Act Rationally

Ans: c, (Why?)
Self driving cars involve following disciplines:
a. Image Processing
b. Image Classification
c. Audio Signal processing
d. Path Planning
e. All of the above

Ans: e (Give examples)

18
 Chinese Room Test

Students:

• Your today’s task is

- to identify the importance of Chinese room test.

-Who gave this concept?
-How human being and machines are classified differently in this test?

19
8-Tile Puzzle: An example

20
8-Tile Puzzle
1. How to search for the
goal state?

2. Do you think, AI is
being used?

1. DFS, BFS

2. No, Why?
 Computer Vision

Computer vision is a field of artificial

intelligence that trains computers to
interpret and understand the visual
world. Using digital images from
cameras and videos and deep
learning models, machines can
accurately identify and classify
objects — and then react to what
they “see” [4].
 Computer Vision

Image processing to computer vision progression

can be broken up into low-, mid- and high-level
processes

Low Level Process Mid Level Process High Level

Input: Image Input: Image Process
Input: Attributes
Output: Image Output: Attributes Output:
Understanding
Examples: Noise Examples: Object
removal, image recognition, Examples: Scene
sharpening segmentation understanding,
autonomous
navigation

Image Processing To Computer V

23
 Login without a password…

Face recognition systems now

Fingerprint scanners on beginning to appear more widely
many new laptops, http://www.sensiblevision.com/
other devices

25
 Object Recognition
Object recognition is a general term to describe a collection of related computer
vision tasks that involve identifying objects in digital photographs.

Object recognition allows robots and AI programs to pick out and identify objects
from inputs like video and still camera images.

The four main tasks are:

• Classification.
• Tagging.
• Detection.
• Segmentation.

The accuracy of segmentation depends on an extensive and often time-consuming26

 Classification and Tagging
In classification the algorithm will only remember that there is a dog, ignoring all other
classes. On the other hand, in tagging, it will try to return all the best classes corresponding
to the image.
PIC: Classification (left) and tagging (right).

Source: https://deepomatic.com
27
 Detection and segmentation

• Detection outputs a rectangle, also called bounding box, where the objects are. It is a
very robust technology, prone to minor errors and imprecisions.

• segmentation identifies the objects for each pixel in the image, resulting in a very
precise map. segmentation identifies the objects for each pixel in the image, resulting in a
very precise map.

28
Source: https://deepomatic.com
Object Recognition

29
Smart Cars
 Optical character recognition
(OCR)
Technology to convert scanned docs to text
• If you have a scanner, it probably came with OCR software

License plate readers

http://en.wikipedia.org/wiki/Automatic_number_plate_recognition

31
Computer Vision Scope
 Natural Language Processing
• Natural Language Processing (NLP) refers to AI method of communicating
with an intelligent systems using a natural language such as English [5].

• The input and output of an NLP system can be −

Speech
Written Text

• Components of NLP
Natural Language Understanding- Mapping the given input in natural
language into useful representations
Natural Language Generation-It is the process of producing meaningful
phrases and sentences in the form of natural language from some internal
representation
 NLP Applications
Applications

• Machine Translation (it is the translation of text or speech by a computer with no human
involvement.)
• Information Retrieval (software program that deals with the organization, storage, retrieval and
evaluation of information from document repositories particularly textual information.
• Question Answering (is concerned with building systems that automatically answer
questions posed by humans in a natural language.
• Dialogue Systems (computer system intended to converse with a human)
• Information Extraction (refers to the automatic extraction of structured information such as
entities, relationships between entities, and attributes)
• Summarization ( refers to the technique of shortening long pieces of text.)
• Sentiment Analysis (tries to identify and extract opinions within a given text across blogs,
reviews, social media, forums, news etc)
 Sentiment Analysis, source and credit: http://ramakavanan.blogspot.com
35
Dialogue Systems, source: Wikipedia
 Robotics
• A robot is a machine: especially one programmable
by a computer, capable of carrying out a complex
series of actions automatically.

• Robots can be guided by an external control device

or the control may be embedded within.

• Robots may be constructed on the lines of human

form, but most robots are machines designed to
perform a task with no regard to their aesthetics.

Source: Wikipedia [2]

 Robotics
A. Mobile Robot
Mobile robots have the capability to move around in their
environment and are not fixed to one physical location. An
example of a mobile robot that is in common use today is
the automatic guided vehicle (AGV).
An automated guided vehicle or automatic guided vehicle is a portable
robot that follows along marked long lines or wires on the floor, or uses
radio waves, vision cameras, magnets, or lasers for navigation [2].

38
 B. Industrial robots (manipulating)
• The International Organization for Standardization gives a definition of a
manipulating industrial robot in ISO 8373:

• "an automatically controlled, reprogrammable, multipurpose, manipulator

programmable in three or more axes, which may be either fixed in place or
mobile for use in industrial automation applications."

39
 C. Educational (interactive) robots
Educational robotics teaches the design, analysis, application and
operation of robots. Robotics may also be used to motivate and facilitate
the instruction other, often foundational, topics such as computer
programming, artificial intelligence or engineering design [2].

Task to students: What is Leachim ?

40
 D. Military Robots
Military robots are autonomous robots or remote-controlled mobile robots
designed for military applications, from transport to search & rescue and attack [2].

41
 Theorem Proving
• Reasoning by theorem proving is a weak method, compared to experts
systems, because it does not make use of domain knowledge.
• Computer used to automate reasoning in a logic
• Theorem proving requires a logic (syntax)
• Applications: program verification, mathematical deduction,

Has a set of axioms and inference rules

Has a strategy on when how to search through the possible applications of
the axioms and rules
 Example
Examples of axioms

(p and (q and r)) => ((p and q) and (p and r))

p \/ ~p

Examples of inference rules

modus ponens p, p and q q

modus tollens P and q, ~q ~p
and elimination P and q p
and introduction p, q p and q

Strategies
forwards - start from axioms, apply rules
backwards - start from the theorem (in general: a set of goals), work backwards to the
axioms
Expert System

44
Expert System

45
46
Advantages of Expert System
Limitations of Expert System

48
 Capabilities of Expert Systems
The expert systems are capable of [5]−
• Advising
• Instructing and assisting human in decision making
• Demonstrating
• Deriving a solution
• Diagnosing
• Explaining
• Interpreting input
• Predicting results
• Justifying the conclusion
• Suggesting alternative options to a problem
Applications of Expert System

50
 References

[1] https://www.merriam-webster.com/
[2] https://www.wikipedia.org/
[3] Stuart Russell, Peter Norvig, Artificial Intelligence: A Modern
Approach, 4th Edition, 2020, Pearson
[4 ] https://www.sas.com
[5] https://www.tutorialspoint.com/artificial_intelligence

51
 Bibliography

Artificial Intelligence (2nd ed) by Elaine Rich and Kevin Knight,

McGraw Hill (1991). ISBN 0-07-100894-2

52
Thank You

53