Scribd
Upload
42 views

CH 1.1 Introduction

This document provides an introduction to artificial intelligence including: - Defining AI and discussing different definitions that have been proposed. - Outlining the history of AI from early programs in the 1950s to recent developments. - Explaining Alan Turing's Turing Test and its proposal of an operational definition of intelligence. - Discussing examples of AI applications including early medical diagnosis systems, game playing, data mining, and more. - Noting that AI is a multi-disciplinary domain that incorporates areas like computer science, engineering, linguistics, psychology and more.

Uploaded by

Kiio Makau
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
42 views

CH 1.1 Introduction

This document provides an introduction to artificial intelligence including: - Defining AI and discussing different definitions that have been proposed. - Outlining the history of AI from early programs in the 1950s to recent developments. - Explaining Alan Turing's Turing Test and its proposal of an operational definition of intelligence. - Discussing examples of AI applications including early medical diagnosis systems, game playing, data mining, and more. - Noting that AI is a multi-disciplinary domain that incorporates areas like computer science, engineering, linguistics, psychology and more.

Uploaded by

Kiio Makau
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 18

Introduction

Intelligence
Defining A.I

History

Turing Test

A.I Applications

Multi-disciplinary domain
Intelligence
 Dictionary definition.
(1) : the ability to learn or understand or to deal with new or trying
situations : REASON; also : the skilled use of reason
(2) : the ability to apply knowledge to manipulate one's
environment or to think abstractly as measured by objective
criteria (as tests)
-Merriam-Webster's Collegiate Dictionary

Prepared by: Okuku B.


Playing games:Draughts

Is a computer more intelligent


if it beats you in a game of draughts?
Prepared by: Okuku B.
Playing games:Scrabble

Is a computer more intelligent


if it beats you in a game of scrabble?
Prepared by: Okuku B.
Intelligence
 Types of intelligence (Multiple intelligence theory, Howard Gardner)

 Linguistic-verbal intelligence
 Logical-Mathematical intelligence
Theoretical foundations
 Musical intelligence
for recognizing different
 Spatial intelligence
talents and abilities in
Intrapersonal intelligence
people

 Interpersonal intelligence
 Naturalist intelligence
 Bodily-Kinesthetic intelligence

 "What makes life interesting, however, is that we don’t have the same
strength in each intelligence area, and we don’t have the same
amalgam of intelligences. Just as we look different from one another
and have different kinds of personalities, we also have different kinds
of minds."

Prepared by: Okuku B.


Defining A.I
There is no agreed definition of the term artificial intelligence.
However, there are various definitions that have been proposed.
These are considered below.
 AI is a study in which computer systems are made that think
like human beings. Haugeland, 1985 & Bellman, 1978.
 AI is a study in which computer systems are made that act like
people. AI is the art of creating computers that perform
functions that require intelligence when performed by people.
Kurzweil, 1990.
 AI is the study of how to make computers do things which at
the moment people are better at. Rich & Knight
 AI is a study in which computers that rationally think are made.
Charniac & McDermott, 1985.
 AI is the study of computations that make it possible to
perceive, reason and act. Winston, 1992
Prepared by: Okuku B.
Defining A.I
 AI is the study in which systems that rationally act are made. AI
is considered to be a study that seeks to explain and emulate
intelligent behaviour in terms of computational processes.
Schalkeoff, 1990.
 AI is considered to be a branch of computer science that is
concerned with the automation of intelligent behavior. Luger &
Stubblefield, 1993.
 ...

Prepared by: Okuku B.


History
 1943 McCulloch & Pitts: Boolean circuit model of brain
 1950 Turing’s “Computing Machinery and Intelligence”
 1950s Early AI programs, including Samuel’s checkers (draughts)
program
 Newell & Simon’s Logic Theorist, Gelernter’s Geometry Engine
 1956 Dartmouth meeting: “Artificial Intelligence” adopted
 1966–74 AI discovers computational complexity,
Neural network research almost disappears
 1969–79 Early development of knowledge-based systems
 1980–88 Expert systems industry booms
 1988–93 Expert systems industry busts: “AI Winter”
 1985–95 Neural networks return to popularity
 1988– Resurgence of probabilistic and decision-theoretic methods
Rapid increase in technical depth of mainstream AI,
“Nouvelle AI”: ALife, GAs, soft computing

Prepared by: Okuku B.


Acting Humanly: Turing Test
 Alan Turing's 1950 article Computing Machinery and Intelligence
discussed conditions for considering a machine to be intelligent
 “Can machines think?”  “Can machines behave intelligently?”
 The Turing test (The Imitation Game): Operational definition of
intelligence.

• Computer needs to posses:Natural language processing, Knowledge


representation, Automated reasoning, and Machine learning
• Problem: 1) Turing test is not reproducible, constructive, and amenable to
mathematic analysis. 2) What about physical interaction with interrogator and
environment?
• Total Turing Test: Requires physical interaction and needs perception and
actuation. Prepared by: Okuku B.
A.I applications
 ALVINN
 MYCIN, PROSPECTOR,..
 Deep Blue
 Data Mining
 ...

Prepared by: Okuku B.


ALVINN
Drives 70 mph on a public highway

30 outputs
for steering
30x32 weights
4 hidden
into one out of
units
four hidden
30x32 pixels unit
as inputs
Prepared by: Okuku B.
Knowledge-based systems
 Medical Diagnosis - MYCIN
 1971, A program that could diagnose blood infections. It had

450 rules
 Mineral Prospecting - PROSPECTOR
 1979, A program that with geological data. It recommended

exploratory drilling sites that proved to have substantial


molybdenum deposits.

Prepared by: Okuku B.


Data Mining

 Which characteristics in the 3-dimensional


structure of new molecules indicate that
they may cause cancer ?
Prepared by: Okuku B.
Data Mining
 An application of Machine Learning techniques
 It solves problems that humans can not solve, because the
data involved is too large, noisy ...

Detecting cancer
risk molecules is
one example.

Prepared by: Okuku B.


Data Mining
 A similar application:
 In marketing products ...

Predicting customer
behavior in
supermarkets is
another.

 Fraud Detection
 1997, Credit card fraud detection

Prepared by: Okuku B.


Branches of A.I
 Machine vision
 Speech synthesis and recognition
 Machine Learning
 Robotics
 Natural Language and understanding
 Problem solving
 Game playing
 ..

Prepared by: Okuku B.


Applications
 Computer
vision
 Image
Recognition
 Language and speech processing

 Robotics

Prepared by: Okuku B.


AI, a Multi-disciplinary domain
 Engineering:
 robotics, vision, control-expert systems, biometrics,

 Computer Science:
 AI-languages , knowledge representation, algorithms, …

 Pure Sciences:
 statistics approaches, neural nets, fuzzy logic, …

 Linguistics:
 computational linguistics, phonetics en speech, …

 Psychology:
 cognitive models, knowledge-extraction from experts, …

 Medicine:
 human neural models, neuro-science,...

Prepared by: Okuku B.

You might also like