Scribd
Upload
21 views18 pages

AI-chapter 1

A University CEP (Continuing Education Program) Students Payment Management System A University CEP (Continuing Education Program) Students Payment Management System

Uploaded by

ephitsegaye7878
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
21 views18 pages

AI-chapter 1

A University CEP (Continuing Education Program) Students Payment Management System A University CEP (Continuing Education Program) Students Payment Management System

Uploaded by

ephitsegaye7878
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/ 18

Chapter one:

Introduction to AI
1. Introduction to AI

2. Approaches to AI – making computer:

2.1. Think like a human (Thinking humanly)

2.2. Act like a human (Acting humanly)

2.3. Think rationally (Thinking rationally)

2.4. Act rationally (Acting rationally)

3. The Foundations of AI

4. Bits of History and the State of the Art


INTRODUCTION

telligence is a property/ability attributed to people, such as to know, to think, to talk, to learn.


Intelligence = Knowledge + ability to perceive, feel, comprehend, process, communicate, judge, learn.

tificial Intelligence

 interdisciplinary field aiming at developing techniques and tools for solving problems.

 study of ideas that enable computers to be intelligent.


INTRODUCTION(1)
Definitions of artificial intelligence according to eight recent textbooks are:

citing new effort to make computers think … “The study of mental faculties through the use of
with minds, … ” (Haugeland, 1985) computational models” (Charniak and McDermott, 1985

ies that we associated with human thinking,


s such as decision-making, problem solving, “ The study of the computations that make it possible
… “ (Bellman, 1978) perceive, reason, and act” (Winston, 1992)

of creating machines that perform functions “A field of study that seeks to explain and emulate
uire intelligence when performed by people” intelligent behaviour in terms of computational proce
l, 1990) (Schalkoff, 1990)

dy of how to make computers do things at “The branch of computer science that is concerned w
t the moment, people are better” (Rich and automation of intelligent behaviour” (Luger and
1991) Stubblefield, 1993)
Todays AI
Goals of Artificial Intelligence
ntific goal: understand the mechanism behind human intelligence.

neering goal: develop concepts and tools for building intelligent agents capable of solving real world problem
ples:
nowledge-based systems:: capture expert knowledge and apply them to solve problems in a limited domain.
mmon sense reasoning systems:: capture and process knowledge that people commonly hold which is not e
mmunicated.
arning systems:: posses the ability to expend their knowledge based on the accumulated experience.
tural language understanding systems.
telligent robots.
1.2. Approaches to AI – making computer
I falls into four categories: Systems that:

Boundarie of AI in 4 dimention
Thinking humanly

The cognitive science


 How do humans think, how does the (human) brain work
 E.g. Conduct experiments with people to try how we reason, learning, remember, predict

hree methods that human to get inside the actual world of human mind.
 Through introspection: try to catch our own thought.
 Through psychological experiment: observing the person in action.
 Through brain imagining: observing the brain in action.
Acting humanly
ring test "Computing machinery and intelligence“

 Operational test for intelligent behaviour

 Not reproducible, not amenable to mathematical analysis

 Major components required for AI: knowledge representation, reasoning, language/image


understanding, learning
Thinking rationally
w of thought approach
Logics, Formalization of knowledge and inference
Represent facts about the world via logic

e logical inference as a basis for reasoning about these facts


 all humans are mortals
Acting rationally
Decision theory: How to make good action choices?
 Set of future states of the world
 Set of possible actions an agent can take
 Utility = gain to an agent for each action/state pair
 An agent acts rationally if it selects the action that maximizes its “utility” Or expected utility i
is uncertainty

Autonomous agents that behave rationally (make the best predictions, take the best
actions)
 on average over time
 within computational limitations (“bounded rationality”)
1.3 AI foundations
herited many ideas, viewpoints and techniques from other disciplines.

investigate
man mind
Theories of reasoning and
learning
AI
(intersection of fields)
Linguistic
Mathematics
he meaning and
Theories of logic probability, decision
ructure of language
CS making and computation
(logic,programming,
algorithm

Make AI a reality
1.4. History of AI

50: Turing
Turing's "Computing Machinery and Intelligence“

56: birth of AI
Dartmouth meeting: "Artificial Intelligence“ name adopted

50s: initial promise


Early AI programs, including
Samuel's checkers program

55-65: “great enthusiasm”


McCarthy: invention of LISP
History of AI
1966—85: Adding domain knowledge
 Development of knowledge-based systems

 Success of rule-based expert systems,

 But were brittle and did not scale well in practice

1986-- Rise of machine learning


 Neural networks return to popularity

 Major advances in machine learning algorithms and applications

1990-- Role of uncertainty


 Bayesian networks as a knowledge representation framework

1995-- AI as Science
 Integration of learning, reasoning, knowledge representation

 AI methods used in vision, language, data mining, etc


Recent AI Successes

 Expert systems: medical, diagnosis, design.

 Speech recognition applications.

 Robots controlling quality in factories.


Can we build hardware as complex as the brain?
How complicated is our brain?
a neuron, or nerve cell, is the basic information processing unit
estimated to be on the order of 10 12 neurons in a human brain
many more synapses (10 14) connecting these neurons
cycle time: 10 -3 seconds (1 millisecond)

How complex can we make computers?


108 or more transistors per CPU
supercomputer: hundreds of CPUs, 1012 bits of RAM
cycle times: order of 10 - 9 seconds
Drawbacks/ Limitations of AI
 it needs program to work that means it needs huge data as input
 unemployment
 it may leads to perform beyong human being
Intelligent Systems in Your Everyday Life
st Office
utomatic address recognition and sorting of mail
anks
utomatic check readers, signature verification systems
utomated loan application classification
ustomer Service
utomatic voice recognition
he Web
dentifying your age, gender, location, from your Web surfing
Automated fraud detection
gital Camera
Automated face detection and focusing
omputer Games
ntelligent characters/agents
Thank you

You might also like