Você está na página 1de 28

ITS462 FUNDAMENTALS OF ARTIFICIAL

INTELLIGENCE

Chapter 1: Introduction

AUTHOR : DIANNE CHEONG LEE MEI


ITS462 Fundamentals of Artificial
Intelligence
Chapter 1 : Introduction
TABLE OF CONTENTS

Learning objectives

Prerequisites

What is Intelligence?

What is Artificial Intelligence (AI)?

Turing Test

Major research and applications of AI

Conclusions

Quiz

References
LEARNING OBJECTIVES

Distinguish between human intelligence and artificial intelligence

Identify the different types of problems for computers to do best

Explain the Turing test


PREREQUISITES

Students have had introductory courses in discrete mathematics,


including predicate calculus, set theory, statistics, and graph theory.

Students have had courses in data structures including trees, graphs,


and recursion-based search using stacks, queues, and priority queues.
WHAT IS INTELLIGENCE?

Intelligence is the ability to learn about, to learn from, to


understand about, and interact with the environment.
ARTIFICIAL INTELLIGENCE

Artificial intelligence (AI) may be defined


as the branch of computer science that is
concerned with the automation of
intelligent behavior.
AI is based on sound theoretical and applied
principles of computer science the data
structures used in knowledge representation,
the algorithms needed to apply that
knowledge, and the languages and
programming techniques used in their
implementation.
Luger, G.F. Artificial
Intelligence: structures and
strategies for complex problem
solving. Sixth edition. Addison
Wesley, 2009.
WHAT IS ARTIFICIAL INTELLIGENCE
(AI)?

The study of computer systems that attempt to model


and apply the intelligence of the human mind
the ability to
act rationally

the ability to
solve novel
problems
the ability to
act like
humans
COMPUTATIONAL MODEL

human behavior human thought

Programs that Programs that operate


behave (externally) (internally) the way
like humans humans do

Computational systems are those that behave intelligently or


rationally
PROGRAM OR HUMAN

not enough to make a program that seems to behave the way humans d

you want to make a program that does it the way


humans do it.
THE TURING TEST

Turing test
A test to empirically determine whether a computer has achieved intelligence

Alan Turing
An English mathematician who wrote a landmark paper in 1950 that
asked the question: Can machines think?

He proposed a test to answer the question :


If a computer could think, how could we tell?"
THE TURING TEST
SIMULATION

Figure 1

In a Turing test, the


interrogator must determine
which respondent is the
computer and which is the
human.
THE TURING TEST

??

The interrogator is only able to communicate with them through a


textual device.

The task of the interrogator is to distinguish between the computer and


the human based on their responses to questions asked over this
device. The machine maybe assumed to be intelligent if the responses
are indistinguishable from that of the human.
THE IMPORTANT FEATURES OF THE TURING
TEST

An attempt to give an understanding (idea or belief) of intelligence.

Confusing and currently unanswerable questions such as:


Does the computer use the appropriate internal processes?
Is the machine conscious of its actions?

The interrogator focus solely on the content of the answers to


the questions.
THE LOEBNER PRIZE

The first formal instantiation of the Turing Test


Dr. Loebner pledged a Grand Prize of $100,000 and a Gold Medal for
the first computer whose responses were indistinguishable from a
human (1990).
Each year an annual cash prize and a bronze medal is awarded to the
most human-like computer.
The winner of the annual contest is the best entry relative to other
entries of that year, irrespective of how good it is in an absolute
sense.
AI APPLICATIONS

Game playing
IBMs Deep Blue - First AI to beat a human chess champion : Garry Kasparov,

Blondie24 - Machine learning program that won a checker tournament

Commercial game AI - Sophisticated AI work for non-academic games


AI APPLICATIONS

Logistics Planning

Trip itineraries - cellphone


application, WAZE, uses AI to
propose driving directions from one
location to another
Dynamic Analysis and Replaning
Tool (DART) - Used during the 1991
Persian Gulf crisis to assist in
managing military resources (over
50,000 people, vehicles and cargo
shipments)
Airline flight scheduling - If flights
are delayed or rerouted, AI
planners are used to figure the
best way to reschedule departures
and arrivals
AI APPLICATIONS

Speech recognition

Airline reservation systems -


Often robust to many different
voice pitches and accents

Automatic transcription -
Monitors language and content
for live radio and television

Transcription software for


captioning whatever someone
says
AI APPLICATIONS

Text processing

Automated language
translation - Altavistas
Babelfish server
Information retrieval - Google
search engine

Text classification and


organization Google news,
SPAM filtering
Document summarization
Columbia Universitys
Newsblaster
AI APPLICATIONS

Biology & Medicine

Diagnosis systems -
Specialists often use
statistical AI tools to
diagnose a patient based on
the symptoms
Genome analysis
software - AI is used to
identify new genes, infer
biochemical pathways,
and compare genomes of
multiple species
AI APPLICATIONS

Vision

Handwriting recognition - US
Postal Service automatically
sorts mail
Face recognition -
Government/bank security
systems

Autonomous Land Vehicle In a


Neural Network (ALVINN);
Uses camera data to
automatically steer a car on a
highway at speeds up to 65
mph (from Washington, DC to
San Diego and back)
AI TREE

Speech
Machine Understanding
Learning
Automatic Robotic

Game
Natural
Playing
Language
Processing
Neural Network
Expert System
Fuzzy Logic
Intelligent
Tutor Genetic
Algorithm
Computer Data Mining
Vision

Linguistics
Computer
Science
Psychology
Management

Philosophy Electrical
Engineering

Philosophy |Mathematics |Economics |Neuroscience |Psychology |


Computer Engineering | Control Theory and Cybernetics |
AI IN A NUTSHELL

Rea Abstract
l
Storage and communication Acquisition, retrieval and use
capability of current technology capability of current technology

Real time computer


vision, Scene Image Natural Classic
understanding and understanding Language Artificial
synthesis Processing Intelligence

Co pts
ty li
a

nc
Re

e
Simulations Multimedia Natural Formal
Computer (video-clips, language descriptions
models images, artifacts Symbolic
Virtual sounds, the (eg: representations
KEY POINTS

AI is the use of computers to do reasoning, pattern recognition,


learning,
or some other form of inference.
AI reasoning is about the significant qualitative features of a
situation.
AI focus on problems that do not respond to algorithmic
solutions. This underlies the reliance on heuristic search as an AI
problem-solving technique.
AI concerns with problem-solving using inexact, missing, or
poorly defined information. The use of representational
formalisms enables the programmer to compensate for these
problems.
Quiz

Click the Quiz button to edit this quiz


QUIZ

Question 1: Select the true statement about intelligence.


Answer:
a. Intelligence is the ability to teach about, to teach for, to
understand about, and interact with the environment.
b. Intelligence is the ability to learn about, to learn from, to
understand about, and interact with the environment.
c. Intelligence is the ability to teach about, to learn from, to
understand about, and interact with the situation.

Question 2: Define Turing Test


Answer:
d. A test to empirically determine whether a computer is intelligence
e. A test to empirically determine whether a computer is good
f. A test to empirically determine whether a computer has achieved
intelligence
QUIZ

Question 3: Identify example of AI


application used in Speech recognition
Answer:
a. Airline reservation systems.
b. Document summarization.
c. Diagnosis systems.
REFERENCES

uger, G.F. Artificial Intelligence: structures and strategies for complex problem s
Sixth edition. Addison Wesley, 2009.

Stuart, R. and Norvig, P. Artificial Intelligence: A Modern Approach.


3rd Edition. Prentice Hall, 2010.

Callan, R. Artificial Intelligence. Palgrave Macmillan, 2003.

evitsky, M. Artificial Intelligence: A guide to intelligent systems. 2nd Edition.


son Wesley, 2005.

5. Module Lecture Notes.

Você também pode gostar