Artificial Intelligence (AI)

stepweedheightsΤεχνίτη Νοημοσύνη και Ρομποτική

15 Οκτ 2013 (πριν από 3 χρόνια και 9 μήνες)

72 εμφανίσεις

Department of Computer Science

AI
-

Introduction

1

of
7

Artificial Intelligence (AI)




The syllabus refers to Computing Curricula December 2001, developed by
IEEE Computer Society and Association for Computing Machinery (ACM)



Intelligent Systems (10 core hours)

IS1.

Fundamental issues in intelligent systems (1 ho
ur)

IS2.

Search and Constraint Satisfaction (5 hours)

IS3.

Knowledge Representation and Reasoning (4 hours)

IS4.

Advanced Search

IS5.

Advanced Knowledge Representation and Reasoning

IS6.

Agents

IS7.

Natural Language Processing

IS8.

Machine Learning and Neural Networks

IS9.

AI Planning Systems

IS10.

Ro
botics



Pre
-
requisites

1.

Mathematics Logic

2.

Data Structure

3.

Probability and Statistics



Grading Policy

Attendance and Class Participation

1
0 %

Assignments (a group = max 4 students)

50

%

Midterm Exam

20

%

Final Exam

20

%


SCORE

GRADE

Score >= 80

A

70 =<
Score < 80

B

60 =< Score < 70

C

50 =< Score < 60

D

Score =< 50

E



References

[RUS95]

Russel, Stuart and Norvig, Peter. 1995.
Artificial Intelligence: A
Modern Approach
. Prentice Hall International, Inc.

[RIC91]

Rich, Elaine and Knight, Kevin. 1991. A
rtificial Intelligence.
McGRAW
-
HILL, Inc. 2nd Edition.

[KUR99]

Kurzweil, Ray. 1999. The age of Spiritual Machines: When
Computers Exceed Human Intelligence. Viking Penguin.

Department of Computer Science

AI
-

Introduction

2

of
7

AI Subject Guide


Week

Topics

Methods

1


Fundamental issues in intelligent systems

Tutorial

2


Search and Constraint Satisfaction



P牯r汥m⁓pa捥s




-
楮io牭ed⁓ea牣r

Tu瑯物a氬⁤楳捵獳ion

3


Advanced Search



䥮formed⁓ea牣r

-

Best
-
First Search: Greedy search, A*

-

Heuristic Functions

Tutorial, discussion

4


-

Memory Bounded Search: IDA*, SMA*

-

Bi
-
dir
ectional Search: BDA*, MBDA*

Tutorial, discussion,
assignment

5




䥴e牡瑩re⁉mp牯remen琠A汧o物瑨ms

-

Hill Climbing

-

Simulated Annealing

Tutorial, discussion

6




䝥ne瑩挠t汧o物瑨m

Tutorial, discussion

7




䝥ne瑩挠t汧o物瑨m

Tutorial, discussion

8


Midterm Exam

Essay,
closebook

9


Knowledge Representation & Reasoning



P牯ro獩瑩sna氠log楣



P牥r楣慴e⁃ 汣畬l猠and⁒ 獯汵瑩tn

Tu瑯物a氬⁤楳捵獳ion






Weak⁓汯l &⁆楬汥爠l瑲t捴c牥



S瑲tng⁓汯l &⁆楬汥爠l瑲u捴c牥

Tu瑯物a氬⁤楳捵獳ion






剥R獯n楮i⁷楴i⁕ 捥牴a楮iy
 onmonoton楣i
汯l楣i
Ⱐ䍥牴C楮iy⁆ 捴c牳Ⱐ䙵z穹⁌og楣i

Tu瑯物a氬⁤楳捵獳ion




Machine Learning and Neural Networks



Mu汴l
-
污le爠re牣数瑲tns…⁂a捫⁐牯raga瑩tn

Tu瑯物a氬⁤楳捵獳ionⰠ
䑥Do p牯r牡r






P牯rab楬楳瑩挠乥i牡氠乥瑷o牫

Tutorial, discussion

14


AI Planning Systems



䙲om⁐牯bl
em⁓o汶楮i⁴o⁐污nn楮i



䝯a氠lta捫⁐lann楮i



䍯C獴牡楮i Po獴楮g

Tutorial, discussion

15


Review assignment

Presentation and
Discussion

16


Final Exam

Essay, closebook


Department of Computer Science

AI
-

Introduction

3

of
7


“The exciting new effort to make
computers
think

… machines with

minds, in the full and
lite
ral sense” (Haugeland, ‘85)


“[The automation of] activities that we associate
with
human thinking
, activities such as
decision making, problem solving, learning …”
(Bellman, ‘78)


“The study of
mental faculties

through the
use of computational models”

(Ch
arniak and McDermott, ‘85)


“The study of the computations that make it
possible to
perceive, reason,
and

act


(Winston, ‘92)

“The art of creating machines that perform
functions that require
intelligence

when
performed by people” (Kurzweil, ‘90)


“The st
udy of how to make
computers do

things

which, at the moment, people do better”
(Rich and Knight, ‘91).


A field of study that seeks to explain and
emulate
intelligent behavior

in term of
computational processes” (Schalkoff, ‘90)


“The branch of computer s
cience that is
concerned with the automation of
intelligent behavior
” (Luger and
Stubblefield, ‘93)


Thinking Humanly: The Cognitive Modeling Approach.

1.

Through introspection: trying to catch our own thoughts as they go by.

But: how do you know that you
understand?

2.

Through psychological experiments.


Acting Humanly: The Turing Test Approach.

The computer would need to possess capabilities: Natural Language Processing, Knowledge
Representation, Automated Reasoning, Machine Learning, Computer Vision, Roboti
cs.


Thinking Rationally: The Laws of Thought Approach.

There are two obstacles to this approach:

1.

It’s not easy to take informal knowledge and state it in the formal terms required by logical
notation, particularly when the knowledge is less than 100 % cer
tain.

2.

There is a big difference between being able to solve a problem “in principle“ and doing so
in practice.


Acting Rationally: The Rational Agent Approach.

Making correct inference is sometimes
part
of being a rational agent, because one way to act
rat
ionally is to reason logically to the conclusion that a given action will achieve one’s goal,
and then to act on that conclusion.

Department of Computer Science

AI
-

Introduction

4

of
7

Some Application Areas of AI

1.

Speech Recognition:

PEGASUS handles transactions of airline reservation.

2.

Game Playing:

Deep Blue

Chess program beat world champion Gary Kasparov.

3.

Computer Vision:



Face recognition programs in use by banks, government, etc.



The ALVINN system from CMU autonomously drove a van from Washington,
D.C. to San Diego, averaging 63 mph day and night, and in a
ll weather
conditions.



Handwriting recognition, electronics and manufacturing inspection,
photointerpretation, baggage inspection, reverse engineering to automatically
construct a 3D geometric model (2D to 3D image conversion).


4.

Mathematical Theorem Provi
ng:
Use inference to prove new theorems.

5.

Expert System:
CyC




Some AI "Grand Challenge" Problems



Translating telephone



Accident
-
avoiding car



Smart clothes



Body LAN



Tutors (Lecturers)



Android (Human Robot): estimated appears in Year 2099 [KUR99])



Figure 1.1

Interactive Wear [KUR99].

Department of Computer Science

AI
-

Introduction

5

of
7

A Fra
mework for Building AI Systems


1.

Perception

Intelligent biological systems are physically embodied in the world and experience
the world through their sensors (senses). For an autonomous vehicle, input might
be images from a camera and range information fro
m a rangefinder. For a
medical diagnosis system, perception is the set of symptoms and test results that
have been obtained and input to the system manually. Includes areas of vision,
speech processing, natural language processing, and signal processing (e
.g.,
market data and acoustic data).


2.

Reasoning

Inference, decision
-
making, classification from what is sensed and what the
internal "model" is of the world. Might be a neural network, logical deduction
system, Hidden Markov Model induction, heuristic sea
rching a problem space,
Bayes Network inference, genetic algorithms, etc. Includes areas of knowledge
representation, problem solving, decision theory, planning, game theory, machine
learning, uncertainty reasoning, etc.


3.

Action

Biological systems interac
t within their environment by actuation, speech, etc. All
behavior is centered around actions in the world. Examples include controlling the
steering of a Mars rover or autonomous vehicle, or suggesting tests and making
diagnoses for a medical diagnosis sy
stem. Includes areas of robot actuation,
natural language generation, and speech synthesis.



Department of Computer Science

AI
-

Introduction

6

of
7

Some Fundamental Issues for Most AI Problems


1.

Representation

Facts about the world have to be represented in some way, e.g., mathematical
logic is one language
that is used in AI. Deals with the questions of what to
represent and how to represent it. How to structure knowledge? What is explicit,
and what must be inferred? How to encode "rules" for inferencing so as to find
information that is only implicitly know
n? How to deal with incomplete, inconsistent,
and probabilistic knowledge? Epistemology issues (what kinds of knowledge are
required to solve problems).

Example
:



"The fly buzzed irritatingly on the window pane. Jill picked up the
newspaper." Inference: J
ill has malicious intent; she is not intending to read
the newspaper, or use it to start a fire, or ...



Given 17 sticks in 3 x 2 grid, remove 5 sticks to leave exactly 3 squares.


2.

Search

Many tasks can be viewed as searching a very large problem space fo
r a solution.
For example, Checkers has about 1040 states, and Chess has about 10120 states
in a typical games. Use of heuristics (meaning "serving to aid discovery") and
constraints.


3.

Inference

From some facts others can be inferred. Related to search. F
or example, knowing
"All elephants have trunks" and "Clyde is an elephant," can we answer the
question "Does Clyde hae a trunk?" What about "Peanuts has a trunk, is it an
elephant?" Or "Peanuts lives in a tree and has a trunk, is it an elephant?"
Deduction
, abduction, non
-
monotonic reasoning, reasoning under uncertainty.


4.

Learning

Inductive inference, neural networks, genetic algorithms, artificial life, evolutionary
approaches.


5.

Planning

Starting with general facts about the world, facts about the effe
cts of basic actions,
facts about a particular situation, and a statement of a goal, generate a strategy for
achieving that goals in terms of a sequence of primitive steps or actions.


Department of Computer Science

AI
-

Introduction

7

of
7

Comparison between Conventional Programming and AI


Criteria

Conventi
onal

AI

Processing

Numeric

Mainly symbolic

Nature of input/output

Must be complete

Can be incomplete

Search

Algorithms

Heuristic

Major interest

Data, information

Knowledge

Reasoning capability

No

Yes

Explanation

Usually not provided

Provided

Struct
ure

Control integrated with information

Control separation from knowledge

























Inference

: A process of drawing conclusion (solution) from set of facts.

Reasoning

:

A

Process of deriving new knowledge from the e
xist knowledge.


Things, events

Information

Knowledge

Degree of
Abstraction

Quantity

Wisdom

Data

generalize

systematize

give a significance

collect and cover