CS 401

Artificial Intelligence

Lecture # 01
Thursday, January 30, 2020
Spring 2020
FAST – NUCES, Faisalabad Campus

Zain Iqbal
[email protected]
CS 401 - SPRING 2020 1
 Brief Intro
• Course that focuses on the study and design
of IntelligentAgents

CS 401 - SPRING 2020 2

 http://media-cdn.tripadvisor.com/media/photo-s/02/d8/76/21/bletchley-park.jpg
ALANTURING

1950 – He proposed the Turing test

to decide if a computer is exhibiting
intelligent behavior.

CS 401 - SPRING 2020 3

Today’sTopics
 Introduction toAI
 History
 Applications
 Agents
 About this course
◦ Organization
◦ Goals/objectives

CS 401 - SPRING 2020 4

Intelligence and Machines – A
perspective
 What is Intelligence?
 Is it possible for a “machine” to be
intelligent?
 Can machines think?
 Can machines decide?
 Can we emulate intelligent behavior in
machines?
 How far can we take it?

CS 401 - SPRING 2020 5

What is Intelligence?
Few definitions…
Webster’s Dictionary definition
The faculty of acquiring and applying
knowledge.
 A lay man’s perception
Mental skill, brightness or high IQ level.

CS 401 - SPRING 2020 6

What is Intelligence?
 More scientific definition
Intelligence is a measure of the success of an
entity in achieving its objectives by interacting with
its environment.

Reveals important points…

 Presence of an environment to observe
intelligent behavior
 Measure goals on a scale to measure
intelligence

CS 401 - SPRING 2020 7

What is Intelligence?
It provides us possibility of intelligent
machines
 The ability to express intelligence depends
on the richness of interaction with the
environment, and on the achievement of
the goals as well as internal mechanisms

CS 401 - SPRING 2020 8

CS 401 - SPRING 2020 9
What is Intelligence?
 So an intelligent entity interacts with its
surroundings and it implies followings:
◦ Some form of getting input
◦ A way to produce output
◦ Ability to process input to give the output
some relevance

CS 401 - SPRING 2020 10

Artificial intelligence is the simulation of
intelligence in machines

CS 401 - SPRING 2020 12

Approaches to AI
 The science of making machines that:

CS 401 - SPRING 2020 13

Think like Human

“Cognitive approach”
Three ways to do this:
• Through introspection
• Through psychological
experiments
• Through brain imaging

CS 401 - SPRING 2020 14

Act like Human

“Turing test approach”

Six disciplines are required:
• Natural language processing,
• Knowledge representation,
• Automated reasoning,
• Machine learning,
• Computer vision,
• Robotics

CS 401 - SPRING 2020 15

Think Rationally

“Laws of thought”
Based on logical inferences.
Obstacles in doing so:
• Not easy to state informal
knowledge in formal terms
• Big difference in solving a
problem in practical and to
solve it in principle

CS 401 - SPRING 2020 16

Act Rationally

“Rational agent approach”

Merits:
• More general than “laws of
thought” approach
• More adjustable to scientific
development

This course is about designing rational/intelligent agents

CS 401 - SPRING 2020 17
HISTORY

CS 401 - SPRING 2020 17

History of AI
• The branch of computer science called Artificial
Intelligence is said to have been born at a conference
held at Dartmouth, USA, in 1956

• The scientists attending that conference represented

several different disciplines: mathematics, neurology,
psychology, electrical engineering, etc

• They had one thing in common:

They all were trying to use the recently developed
computers to simulate various aspects of human
intelligence

CS 401 - SPRING 2020 18

Abridged history of AI
 1943 McCulloch & Pitts: Boolean circuit model of
brain
 1950 Turing's "Computing Machinery and
Intelligence"
 1956 Birth of AI – Dartmouth:"Artificial Intelligence“
adopted
 1950s Early AI programs, including Samuel's checkers
program, Newell & Simon's LogicTheorist,
 1952-69 Look,Ma,no hands!
 1966-73 AI discovers computational complexity
No progress seemed in Machine Evolution
Neural network research almost disappears
 1969-79 Early development of knowledge-based systems
 1980-- AI becomes an industry
 1987-- AI becomes a science
 1995-- Emergence of intelligent agents
 2001-- Availability of very large data sets
CS 401 - SPRING 2020 20
19
Another Perspective of Intelligence

According to Douglas Hofstadter these are:

- To respond to situations flexibly

If the same response is exhibited each time, the
behavior is called mechanical.
To survive in changing environments, one need to
exhibit innovative behavior.

- To make sense out of ambiguous or contradictory messages

We understand such messages because our
knowledge and experience allows us to place them in
context.
(e.g. time flies like an arrow)

CS 401 - SPRING 2020 20

Another Perspective of Intelligence

- To recognize the relative importance of different elements

of a situation
(e.g. quality versus price of a product)

- To find similarities between situations despite differences

which may separate them
(e.g. chairs in two different pictures)

- To draw distinctions between situations despite similarities

which may link them
(e.g. differences in two cars)

These abilities are largely due to knowledge and experience,

which allows you to place an information in its wider context

CS 401 - SPRING 2020 21

There are many specialized subfields (each of them is a
separate course - often graduate course)

MAJOR AREAS OFAI

CS 401 - SPRING 2020 22

Natural Language Processing
 Goal is to enable people and computers to
communicate in ordinary or natural English.
 Speech technologies
◦ Automatic Speech Recognition (ASR)
◦ Text-to-speech synthesis (TTS)
◦ Dialog systems
 Language ProcessingTechnologies
◦ Machine translation
◦ Information extraction
◦ Information retrieval
◦ Text classification, spam filtering
CS 401 - SPRING 2020 22
http://3.bp.blogspot.com/-dSRbRaH31QI/UEehOEs3hmI/AAAAAAAAAK8/tGTmTbI9ueg/s1600/expert+system.png

Expert Systems
 A computer program designed to act as
an expert in particular domain.
 An ES includes:
◦ Knowledge base (collection of facts and rules)
◦ Inference engine (applies rules to known facts to
deduce new facts)

CS 401 - SPRING 2020 23

 Robotics

https://alexrosephotos.files.wordpress.com/2012/01/img_0551.jpg
http://labintsis.com/wp-content/uploads/2010/07/medical-robot-1.jpg

http://indulgy.ccio.co/y5/b6/uA/kistcirosroboCtSw4o0rl1CS
d2-0401
S1P2-Rko
SPRING
INreGasa2020
2la0d1r6obotrobotics5.jpg 24
25
https://encrypted-tbn1.gstatic.com/images?q=tbn:ANd9GcTPj0W6FqH0Ud3Q0emZJXVk4vdrKDh4-iCtFZW3UEWpi_pT2jCE
Computer Vision

http://cs.brown.edu/people/hays/research/obj_detect_teaser.jpg
CS 401 - SPRING 2016
2020 25
26
https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRcj5SAy 9qlEnObMJ7UMaBir1Xjrf8mT RCIZ85lRevZTTmo jIMU_g
 Game Playing
http://upload.wikimedia.org/wikipedia/commons/b/be/Deep_Blue.jpg

http://www-03.ibm.com/ibm/history/ibm100/images/icp/A138918I23240Y22/us eC
CS
n_Su4401
s0_1_ib-m
-SPSPRING
1R00IN G702020
200_1s6eries checkers 620x350.2jp27
6g
Planning and decision support
 Intelligent programs designed to provide
active assistance in the planning process.
 During the 1991 Gulf War, US forces
deployed an AI logistics planning and
scheduling program that involved up to
50,000 vehicles,cargo,and people
 NASA's on-board autonomous planning
program controlled the scheduling of
operations for a spacecraft

CS 401 - SPRING 2020 27

Automatic Programming
 Computer system that could develop
program by itself, in response to and in
accordance with the specifications of a
program developer

CS 401 - SPRING 2020 28

Intelligent CAI

http://www.bobnewell.net/checkers/images/straightl2.jpg
http://media1.my.88db.com/my_UploadFiles/2006/12/2C6S/441600CS 401
1E-9D SPB-RSPRING
-AINDG082020 30
2-4051B68-9419-E943EA5957D3.jpg 29
How far AI goes?
 Internet search
 Scheduling
 Logistics
 Human Computer Interaction (HCI)
 Games
 Education
 Auction design
 Fraud detection
 Diagnosis
 General reasoning
 and many more…
Our focus is on AI fundamentals
CS 401 - SPRING 2020 30
COURSE
ORGANIZATION

CS 401 - SPRING 2020 31

Introduction, history
and applications
Problem solving by
search

Game trees

Knowledge based
reasoning

Planning

Expert systems

Artificial Neural
Networks

K-Mean
Naive Bayes classifier
Genetic algorithm
CS 401 - SPRING 2016
2020 32
33
 Tentative Marks Distribution
Item Name Quantity Marks (%)

Home work Very often 5%

Quizzes 06 [BEST 05: announced] 15%

(3 abs. each)

Assignments / 03-05 15%

Project

Mid Exams 01 25%

Final Exam 01 40%

40% marks are required at minimum to PASS this course

No retakes for missed quizzes
Assignment late work policy: 30% marks deduction (per day after the deadline)
CS 401 - SPRING 2020 34
Course Books

CS 401
01 - SPRING 2016
2020 35
CS 4
Honor Code
 Dishonesty will NOT be tolerated.
 All parties involved in any kind of cheating
will be punished equally.
 It will result in negative marks in the
corresponding work at least.

CS 401 - SPRING 2020 37

General Guidelines
 Be regular & punctual in the class.
 Maintain class discipline.
◦ Usage of mobile phones and/or laptops is
prohibited.
 Visit
course tab on SLATE regularly for
updates.
 Confirm your scores as soon as they are
updated, no changes will be made later.

CS 401 - SPRING 2020 38

General Guidelines
 Start working on projects/assignments
right from the first day.
 Read book(s).
 Come prepared in the class.
 Class participation is encouraged.
 Raise your hand before you speak.

CS 401 - SPRING 2020 39

Collaboration
• You are expected to work in group of
two
• What constitutes plagiarism
• Talking about the assignments/home works
with anybody other than an official teammate
• Looking at existing solutions
• Submitting solutions not worked out by the
team members

CS 401 - SPRING 2020 40

Reading Material
 Russell & Norvig: Chapter # 1
 David Poole: Chapter # 1

CS 401 - SPRING 2020 43