0% found this document useful (0 votes)
5 views32 pages

Ai Lec 1

Ai lecture advance ai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
5 views32 pages

Ai Lec 1

Ai lecture advance ai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 32

Artificial intelligence

Lecture #1,2
Iffat Razzaq MS(CS)
Course contents
 Introduction to Artificial Intelligence
 Problem Solving
 Genetic Algorithms
 Searching
 Learning
 Reasoning
 Expert Systems
 Uncertainty (Introduction, Classical sets, Fuzzy sets, Fuzzy
logic, Fuzzy system)
 inference Introduction to Learning (Symbol-based,
Connectionist, Artificial Neural Networks supervised and
unsupervised)
 Knowledge representation
 Intelligent system design
 Machine learning
 Natural language processor
 Planning, Advanced Topics (Computer vision, Robotics, Soft-
computing Clustering), Conclusion.
INTRODUCTION TO ARTIFICAL INTELLIGENCE
 What is intelligence?
 Features of intelligence
 what is AI? (Definitions)
 System that thinks like human
 System that acts like human
 History of AI
Intelligence?
Are the things shown below, intelligent?
what is intelligence?
 Intelligence is an umbrella term used to describe a property
of mind that includes many related abilities, such as the
capacity to
 Reason
 Plan
 Solve problems
 Think abstractly
 Comprehend ideas
 Use language
 learn
Ex 1: searching a path …
 Different mice might follow different paths based to their intelligence. In other
words: the problem can be solved in many ways
 Ability to solve problems demonstrates intelligence
Ex 2
 Next number in the sequence …
 Consider the following sequence
1,3,7,13,21, …
What is the next number????
Key: adding the next even number …
1+2=3; 3+4=7; 7+6=13; 13+8=21; 21+10=31
1,3,7,13,21,31

Ability to solve problems demonstrates intelligence


The ability to think, plan & execute
 Time table development
 Complexity
 Thinking
 Training
 Planning
 Execution
Memory & information processing
demonstrate intelligence
 The ability to think, memories, plan and execute.

Doctor Example
Ambiguity
 Things not clear
 Height example
 Ability to answer fuzzy questions
 The ability to handle, treat and execute ambiguous things.
Understanding & perception
 The ability to understand and perceive things demonstrate
intelligence.
 Example
Watching a lecture.
Voice mute
Recognition & learning
 The ability to learn and recognize demonstrate intelligence.

Example
See faces & match
Get up of an individual
So let’s summarize …
 Ability to solve problems
 Ability to plan and schedule
 Ability to memorize and process information
 Ability to answer fuzzy questions
 Ability to learn
 Ability to recognize
 Ability to understand
 Ability to perceive
 And many more …
What if?
 A machine searches through a mesh and find a path?
 A machine solves problem like the next number in a
sequence?
 A machine develops a plan?
 A machine diagnoses and prescribe?
 A machine answer ambiguous question?
 A machine recognizes fingerprints?
 A machine understands?
 A machine perceives?
 A machine behaves as HUMANS do?
What is artificial intelligence?
 Making computer that thinks.
 The automation of activities we associate with human
thinking, like decision making, learning … ?
 The art of creating machines that perform functions that
required intelligence when performed by people?
 The study of mental faculties through the use of
computational models ?
 The study of computations that make it possible perceive,
reason and act?
 A branch of computer science that is concerned with the
automation of intelligent behaviour?
Definitions of AI
System that think like HUMANS
 In 1978, the applied mathematician Richard Bellman
defined AI as the automation of activities
associated with human thinking, which include
decision- making, problem solving, and
learning.
 “The study of computation that make it possible
to perceive, reason and act” (WINTSON 1992)
SYSTEM THAT act LIKE HUMANS
 “The branch of computer science that is
concerned with automation of intelligent
behaviour” (Lugar and Stubblefield, 1993)
 “ The art of creating machines that perform
functions that require intelligence when
performed by people” (Kurzweil 1990)
Why study AI?

LABOUR

SEARCH ENGINES

APPLIANCES

SCIENCE

Medical diagnosis
What else?
Honda Humanoid Robot

Walk

Turn

Stairs
Family Robot
A brief history of AI
 A Brief History of AI
 1943: McCulloch and Pitts propose a model of artificial
neurons
 1956 Minsky and Edmonds build first neural network
The Dartmouth Conference (1956)

 John McCarthy organizes a two-month workshop for


researchers interested in neural networks and the study of
intelligence
 Agreement to adopt a new name for this field of study:
Artificial Intelligence
AI’s official birth: Dartmouth, 1956
“An attempt will be made to find how to make machines
use language, form abstractions and concepts, solve
kinds of problems now reserved for humans, and
improve themselves. We think that a significant
advance can be made if we work on it together for a
summer.”
John McCarthy and Claude Shannon
Dartmouth Workshop Proposal
1952-1969 Enthusiasm
 Checkers player
 Lots of work on neural networks
1966-1974 Reality
 AI problems appear to be too big and complex
 Computers are very slow, very expensive, and have very
little memory (compared to today)
1969-1979 Knowledge-based systems
 Birth of expert systems
 Idea is to give AI systems lots of information to start
with
1980-1988 AI in industry:
 First successful commercial expert system
 Some interesting phone company systems for diagnosing
failures of telephone service
1990s to the present:
 Increases in computational power (computers are cheaper,
faster, and have tons more memory than they used to)
 An example of the coolness of speed: Computer Chess
Cool things AI is doing now
 Speech recognition
 Face recognition
 Automated reasoning
 Machine learning
 Expert system
 Intelligent cars
 Voice recognition
 Health monitoring
 Companion robots
Many more

You might also like