0% found this document useful (0 votes)
81 views439 pagesAI Technical Book
The document outlines the syllabus and concepts related to Artificial Intelligence (AI) as per the GTU curriculum, including definitions, types of AI, and the foundational disciplines contributing to AI development. It discusses the differences between strong and weak AI, various AI techniques, and the historical context of AI research. Additionally, it highlights the distinctions between human intelligence and machine intelligence, along with examples of expert systems in the AI field.
Uploaded by
Rishi VasishthaCopyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
0% found this document useful (0 votes)
81 views439 pagesAI Technical Book
The document outlines the syllabus and concepts related to Artificial Intelligence (AI) as per the GTU curriculum, including definitions, types of AI, and the foundational disciplines contributing to AI development. It discusses the differences between strong and weak AI, various AI techniques, and the historical context of AI research. Additionally, it highlights the distinctions between human intelligence and machine intelligence, along with examples of expert systems in the AI field.
Uploaded by
Rishi VasishthaCopyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
/ 439
Sar
ETA TAm LU
THEA
SUT COtOE c CD
AAs Per New Syllabus - GTU - SEM VIl (GE/CSE)
Seri ase yeaa
STU Ie Reece ILE NU oe
COTM MNO a GOA Ae CED
« Chapterwise Solved GTU Questions Summer 2012 to Winter 2022
© Solved GTU Question Papers Winter 2021 to Winter 2022
first edition : july 2021
TECHNICAL
DUCT STATE LEI Ce
2 PUBLICATIONS
ssncetses An Up-Thrust for Knowledge Artificial Intelligence
- The Concept
Syllabus
What is AI? : The AI Problems, The Underlying Assumption, What is an AI Techniques, The Level
Of The Model, Criteria For Success, Some General References, One Final Word.
Contents
1.1. The Concept of Artificial Intelligence (AI)... ... Winter-12,14,16,17,19,
- Summer-18, 20-
1.2 Al Problem
1.3. The Underlying Assumption
1.4 What is an Al Technique ?
1.5 The Level of the Model ..
1.6 Chiteria for Success
1.7 Some General References
1.8 Al Terms
1.9 The Environments
1.10 Different Types of Agents
1.11 Designing an Agent System
1.12 One Final Word
1.13 University Questions with Answers computer programs, workin,
8
ction developing ©
Introd ‘ses suc 2 i iret
ities soning, understandin,
activi reasoning, 8 langua,
in ,, are said to demand “intell
: tomobile are gence"
shes even dniviNB = sult that can perform tasks such as these
ve that can dia; 5
ters systems BNOSE disease
eral compo compu! ,
s al GC man Speech and natural Jangaes ae
atic equations certain degree of artificial intelligence
7 is that "How to think’
tivities and systems Is f ! OR
ch act roxess of thinking has various stops ig
‘te a world that is made up of tiny
preceive, understands PT
complex things or sit decal
‘ wre eld of AC aot just atempes 19 ST
entities.
[EET Various Definitions of AI
defined as the branch of computer science that is concerned with the
4 but also it builds intelligent
1. Al may be
automation of intelligent behaviour. (Luger - 1993)
2. Systems that thinks like human.
think ... machines with minds, in the
. The exciting new effort to make computers
full and literal sense. (Hallgeland - 1985)
“The automation of activities that we associate with human
as devision making, problem solving, learning ...” (Bellman - 1978)
thinking, activities such
fe
5. Systems that act like humans.
wine creatirg machines that perform functions that require intellige
by people’. (Kurzweil - 1990)
7. "The stud
are beth of how to make computers do things at which, at the moment, peopl
~ ich end Knight - 1951),
8. Systems that think rtionally
9. The study of mental
faculti i
and McDermott - 1985) ties through the use of computational models: (Chast
0
Tortana: ee
ace, when
a Artic! intelligence 1-3 Artificial Intelligence - The Cona
10, "The study of the computations that make it possible to perceive, reason and ac
(Winston - 1992)
11. Systems that act rationally
12. ‘Computational intelligence is the study of the design of intelligent agents’. (Poc
et al - 1998)
13. "AI is concerned with intelligent behaviour in artifacts". (Nilsson - 1998)
* These definitions vary along two main dimensions. First dimension is the thoug
Process and reasoning and second dimension is the behaviour of the machine.
® The first seven definitions are based on comparisons to human performance wh«
as remaining definitions measure success against an ideal concept of intelligen
which we call rationality. A system is rational if it does the "right thing" giv
what it knows. Historically, there are four approaches that are followed in .
These four approaches are Acting Humanly, Thinking Humanly, Thinki
Rationally and Acting Rationally. Let us consider four approaches in detail,
1) Acting Humanly
* Turing Test : For testing intelligence Alan Turing (1950) proposed a test called
Turing test. He suggested a test based on common features that can match w
the most intelligent entity - human beings.
Computer would need to possess following capabilities :
a) Natural language processing - To enable it to communicate successfully
English.
b) Knowledge representation to store what it knows, what it hears.
©) Automated reasoning to make use of stored information to answer questic
being asked and to draw conclusions.
4) Machine learning to adapt to new circumstances and to detect and make n
Predictions by finding patterns,
Turing also suggested to have physical interaction between interrogater a
computers. Turing test avoids this but Total Turing Test incudes video signal
that the interrogator can test the subject's perceptual abilities, as well as
opportunity for the interrogator to pass the physical objects "through the hatch".
To pass total turing test in addition, computer will need following capabilities.
©) Computer vision to perceive objects.
f) Robotics to manipulate objects.
2) Thinking Humanly
. As we are saying that the given program thinks like human it we should kn
that how human thinks. For that, the theory of human minds needs to
TECHNICAL PUBLICATIONS® - An up thrust for knowledge Artificial Intsligence - The
a
ob ei
1 Py
ee tion ie. trying ty
— ough ee ti cy ,
eat ——— sg tis a ological experiments eh
: a goby and Hm gars matches corresponding
” i Sevam’s mechanis
Se ee ive scenes ae
comput OE an ay BE nary field OE oe om ae Pry,
olf that is, WE * pe tal techniques from PSycholog
te operating ae and expe of the workings of human mint
computet ,
ch
thought approst by Aristotle. This idea p;
ys
app’
Rati net was PIOl ‘i
3) Thinking > of “Right inks was PF always yielded correct conclusions y
For example, eae or
“Ram is mortal to gover the operation in the ming; ihe,
‘These laws of thought Were sp te implemented to create intel
‘ study initiated the field called logic ¥! tigen
systems
a something that acts. But computer agents ary
in aggeto do) is ie B f
. oul a more other attributes that distinguish them from just the
er vei they need to operate under autonomous control, perceiving
the revicerenent, persatng over 2 prolonged time period, adapting to change
and boing capable of taking on another gos ‘A rational agent is expected to act
so as to achieve the best outcome or when there is uncertainity to acheive best
expected outcome.
The laws of thought emphasis on correct inference which should be incorported in
rational agent.
The Foundation of Al
* Now we discuss the various disciplines that contributed ideas, viewpoints and
techniques to Al.
* Philosophy provides base to Al by providing theories of relationship between
physical brain and mental mind, rules for drawing valid conclusions. It also
Provides information about knowledge origins and the knowledge leads to action.
* Mathematics gives strong base to AI to develop concrete and formal rules for
drawing valid conclusions, various method
it " for date i iquues
to deal with uncertain information. computation and techniqué
TECHNICAL PUBLICATIONS® An up tat for nici! Inteligence 1-5 ‘Artificial Intetigence - The Concept
+ Economics support Al to make decisions so as to maximize
payoff and make
decisions under uncertain circumstances.
«Neuroscience gives information which is related to brain processing, which helps
‘Al to develope date processing theories.
+ Phychology provides strong concepts of how humans and animals think and act
which helps AI for developing process of thinking and actions.
ERES The Strong and Weak AI
«After taking brief look at various disciplines that contribute towards AJ, row let
dis look. at the concept of strong and weak Al which also gives basic foundation
for developing automated systems.
FREED strong AI
«This concept was put forward by John Searle in 1980 in his atticle, "Minds, Brains
and Programs’. Strong form Al provides theories for developing some form of
computer based Al that can truly reason and solve problems. A strong form of Al
is said to be sentient or self aware.
«Strong Al can be categorized as,
+ Humandike AI - In which the computer program thinks and reasons much like a
human-mind.
© Nonchuman-like AI - In which the computer program develops 2 totally
non-human sentience, and a non-human way of thinking and reasoning.
[1.1.42 aN
© Weak artificial intelligence research deals with the creation of some form of
computer - based AI that cannot truly reason and solve problems. They can reason
and solve problems only in a limited domain, such a machine would, in some
ways, act as if it were intelligent, but it would not possess true intelligence.
There are several ficlds of weak AI, one of which is natural language. Much of the
work in this field has been done with computer simulations of intelligence based
on predefined sets of rules. Very little progress has been made in strong Al.
Depending on how one defines one's goals, a moderate amount of progress has
been made in weak Al.
TECHNICAL PUBLICATIONS® - An up thrust for knowledge + NASA's Remote AR Tg
eg. diagnosis
can do jones
occurred
EER) Gore Proyino named as Deep Blue defeated world cheyg
y EM match in 1997 Such type of gaming
Control
EEE poorer sasion evsiem was tamed xo sear cal 10 Keep it following
«The ALVINN computer in which 98 % of the time contro} was
made | 2850 miles #
gees aly of the time human took over Al can give
with the sy
theories to develop such systems
EREZ] Diegnosis
+ Heckerman 1991) describes a case where a leading expert on hymph node
thology scoffs at a program's diagnosis
Cpls te diegoes The machine points out the major factors influencing its
decision and explain interaction of several of the symptoms in thus case. If such
diagnostic programs are developed using Al then highly accurate digmonis can be
made
Logistic Planning
In 1991 during the persion Gulf Crisis US. forces deployed a dynamic analysis
and replanning tool name DART for automated logistics planning and scheduling
for transportation.
* Al can provide techniques for making fast and accurate plans.
EER] Rovceis
* For doing complex and critical tasks systems can be devel Al
r using
loped
* Foreg Surgeons can use robot assistants in microsurgery which can generate 3D
“ision of pabents intemal anatomy Artificial Intetigance 1-7
Language Understanding and Problem Solving
PROVERB is computer program which expert in solving crossword purzles
Tr can make use of constraints or possible word fillers, a large database of past
Puzzles and variety of information sources including dictionaries and online
databases. Such as a list of movies and the actors that appears in them.
AT does not generate magic or science fiction but rather it can develops science,
engineering and mathematics system
Recent progress in understanding the theoretical basis for intelligence has gone
hand in hand with improvements in the capabilities of real systems. The subfields
of Al have became more integrated and AI has found common ground with other
disciplines
EERE Human Ve Machine
EER] Wi Machine behave Exactly as Human 7
+ Here are the considerable difference between human and machine.
1) Machines do not have life, as they are mechanical. On the other hand, humans
are made of flesh and blood; life is not mechanical for humans.
2) Humans have feelings and emotions and they can express these emotions.
Machines have no feelings and emotions. They just work as per the details fed
into their mechanical brain
3) Human can do anything original and machines cannot
4) Humans have the capability to understand situations and behave accordingly
On the contrary, machines do not have this capability,
5) While humans behave as per their consciousness,
they are taught
6) Humans perform activities as per their o
machines only have an attficial intelligence,
TERE! Comparisons between Human and Machines
1) Brains are analogue ; machines are digital.
2), The brain uses content-addressable memory; In machine, information in memory is
accessed By polling its precise memory address. This is known as byte-addressuble
memory.
3) The brain is a massively parallel machine ; machines are modular and serial
4) Processing speed is not fixed in the brain; machine has fixed speed specification
5) Brains short - term memory is not like RAM.
machines just perform as
WN intelligence. On the contrary,
TECHNICAL PUBLICATIONS® - An up thrust for knowledge Artificial inteligence - The
—
tO
ve aisincton can be made with respect 10 the bra,
or
trical logic gates
management are performed by the
Same
Artificial intelligence
6) No hardware / softwa’
ore complex than ele
memory
mind.
7) Synapses are far m
8) Unlike machine, processing and
components in the brain.
9) The brain is a self - organizing system
10) Brain have bodies, the brain is much, much digger
List of Expert Systems Influential in AI Field
1. MACSYMA ~ Advised the user on how to solve complex maths problems,
2. DENDRAL - Advised the user on how to interpret the output from 4 el
spectrograph.
4. CENTAUR INTERNIST, PUFF, CASNET - Are all medical expert systems
various purposes
4. DELTA - Locomotive engineering.
5. Drilling Advisor - Oilfield prospecting:
6. Exper Tax - Tax minimisation advice.
7, XSEL - Computer sales.
& PROSPECTOR - Interpreted geological data as potential evidence for minera
than any [current] machine
deposits. (Duda, Hart, in 1976)
9. NAVEX - Monitored radar data and estimated the velocity and position of the
space shuttle. (Marsh, 1984)
10. R1/XCON - Configured VAX computer systems on the basis of customer's needs,
(Mc Dermott, 1980)
11. COOKER ADVISER - Provides repair advice with respect to canned soup
sterilizing machines. (Texas Instruments, 1986)
2 = MANAGEMENT ASSISTANT - Serutinised the data from hospitl
+ support machines, and provided accounts of the patient's conditions.
(Fagan , 1978)
13. MYCIN -
SIN - Diagnosed blood infections of the sort that might be contracted in
hospital
14 CROP AD} -
VISOR - Developed by ICI to advise cereal grain farmers on appropriate
& fertilizers and pesticides for their farms.
3. OPTIMUM - AIV "
~ is a planner used by :
assembly, integration and verification oa Riopel Space Agency to help in the
TECHNICA
PUBLICATIONS? - An up anrust for knowledge Artificial inteligance - The Concept
“Artiete|Inteligence _
Al Problem
+ Much of the early work in AI focused on formal tasks, such as game playing and
theorem proving. For example chess playing, logic theorist was an early attempt to
prove mathematical theorems. Game playing and theorem proving share the
property that people who do them well are considered to be displaying
intelligence.
+ Despite this it appeared that computers could perform well at those tasks by being
fast at exploring a large number of solution paths and then selecting the best one.
But no computer is fast enough to overcome the combinatorial explosion generated
by most problems.
we do every day for instance, when we
«Al focusing on the sort of problem solving
decide to get to work in the morning, often called commonsense reasoning. In
investigating this sort of reasoning Newell, Shaw, and Simon built the General
Problem Solver (GPS), which they applied to several commonsense tasks as well
performing symbolic manipulations of logical expression. However no attempt was
made to create a program with a large amount of knowledge about a particular
problem domain. Only quite simple tasks were selected.
+ As Al research progressed and techniques for handling larger amounts of world
knowledge were devel in dealing with em sol in ialized
S WING,
domains such as medical diagnosis and chemical analysis.
Perception (vision and speech) is another area for Al problems. Natural language
understanding and problem solving in specialized domain are other areas related
to AI problems. The problem of understanding spoken language is perceptual
problem and is hard to solve from the fact that it is more analog related than
digital related. Many people can perform one or may be more specialized tasks in
which carefully acquired expertise is necessary. Examples of such as tasks include
engineering design, scientific discovery, medical diagnosis, and financial planning.
Programs that can solve problems in these domains also fall under the aegis of
Artificial Intelligence.
© The tasks that are targets of works in AI can be categorized as follows :
1, Mundane tasks - Perception (Vision and Speech), Natural language
(Understanding, Generation, Translation, Commonsense reasoning, Robot
control)
2. Formal tasks - Games (Chess, etc.), Mathemati i
, etc.), tics (Geometry, Logic, ral
calculus, etc.) Apeemneeg RS e
3 &E - ineeris i 7
ae ai Engineering (Design, Fault finding, Manufacturing planning),
‘ientific analysis, Medical diagnosis, Financial analysis
TECHNICAL PUBLICATIONS® - An up thrust for knowledge Artificial inteitige
mnie! inteligence .
OS iy
0
Arnot ioigaee eral of the cates
ow to perform '35K5 TO dard order, py Smt
va fio wer ry axils in 2 ler. First oy,
nuew list learn the a? ills are learned. Later expert skills
onsense Se acquired. Earlier Skills are eagigr "th
aterized duplication than the later, more speci, M4
Po tal work in AI work was concentrateg 2!
h
<
me
For this reason much of ee
early areas. ishing most as a practical gj;
Al is flourishing al di,
The probes aren where 20 Al 8 DN lized experioe wi
edge. Expert systems (AI programs) noy * ty
Poy the domains that
pened onsense know! a te
t solving part, or perhaps all, of me
