Introduction to Artificial Intelligence

CS6659 : ARTIFICIAL INTELLIGENCE

1

“I believe that at the end of the century the use of words and general educated opinion will have altered so much that one will be able to speak of machines thinking without expecting to be contradicted.” 

― Alan Turing, Computing Machinery and Intelligence

Objectives• Study the concepts of Artificial Intelligence.

• Learn the methods of solving problems using Artificial Intelligence.

• Introduce the concepts of Expert Systems and Machine Learning.

2

References• Kevin Night and Elaine Rich, Nair B., “Artificial Intelligence (SIE)”,

McGraw Hill- 2008.

• Dan W. Patterson, “Introduction to AI and ES”, Pearson Education, 2007.

• Peter Jackson, “Introduction to Expert Systems”, 3rd Edition, Pearson Education, 2007.

• Stuart Russel and Peter Norvig “AI – A Modern Approach”, 2nd Edition, Pearson Education 2007.

• Deepak Khemani “Artificial Intelligence”, Tata Mc Graw Hill Education 2013.

3

What is AI?

4

What is AI?

5

Interesting Facts about Artificial Intelligence

6

Interesting Facts about Artificial Intelligence

7

Interesting Facts about Artificial Intelligence

8

Artificial Intelligence Pets (widely available by 2025)

9

Artificial Intelligence Can Learn

10

AI Will Become Smarter Than Humans

11

Father of Artificial Intelligence

12

The father of Artificial Intelligence is British mathematician Alan Mathison Turing. In 1950 he declared that in the future there would be a machine that would duplicate human intelligence. He devised a specialised test, known as the “Turing Test”, to be used to prove artificial intelligence. In the test, a human and a computer hidden from view would be asked random identical questions. If the computer was successful, the questioner would be unable to distinguish the machine from the human.

13

2015

14

• In artificial intelligence Robots are doing the grunt work in factories.

• Driverless cars have become a reality.

• WiFi-enabled Barbie uses speech-recognition to talk (and listen) to children.

• Companies are using AI to improve their product and increase sales.

• AI saw significant advances in machine learning.

2016

15

• Deep learning

• AI replacing workers

• Internet of Things (IoT)

• Breakthroughs in emotional understanding

• AI in shopping and customer service

• Ethical questions

• A problem with representation

INTRODUCTION TO AI AND PRODUCTION

SYSTEMS

16

Introduction to AI• Involves the techniques which could make a computer

to perform tasks similar to that performed by a human

• Categorized under Computing Methodologies (ACM)

• A study of solutions for problems that are difficult or impractical to solve with traditional methods, which supports everyday applications such as email, word-processing, search, as well in the design and analysis of autonomous agents that perceive their environment and interact rationally with the environment.

17

Introduction to AI (Contd..)• Initially viewed as a technique of solving day to day

problems

• also termed common sense reasoning

• certain ideas on understanding natural languages – Natural Language Processing

• Recent researches emphasize on AI as an intelligence which requires knowledge

18

Introduction to AI (Contd..)• The knowledge captures generalizations. From this, it

could be inferred that the situations that share important properties are grouped together.

• It can be understood by people who provide it.• It can be easily modified to correct errors and to reflect

changes in the world and in our world view.• It can be used in most situations even if it is not

accurate or complete.• It can be used to identify the narrow range of

possibilities.

19

Problem formulation• Involves 4 steps

1. Define the problem precisely. The definition must comprise of precise specification of the initial situation as well the final situation with acceptable solutions to the problem.

2. Analyse the problem.3. Isolate and represent the task knowledge which is

required to solve the problem.4. Choose the best problem-solving technique(s)

and apply it (them) to the particular problem.

20