7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 1/22

PROFESSOR:- MR. PATVARDHAN

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 2/22

1. RAVI KANT SINGH (40)

2. SANTOSH SINGH (41)

3. SIDDHARTH ADVANI (01)

4. GIRISH LUNDWANI (20)

5. ANIL MARU (21)

6. PRABHAT SINGH (39)

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 3/22

Artificial Intelligence (A.I.)

By: “The Feeders”

Estabillo, Jan Mikael C.

Fajardo, Kenneth Jude L.

Mondejar, Darlon Jay C.

Monsalud, Benjie R.Rivera, Robert Erwin O.

Information taken from

http://didyouknow.org/ai/ and

http://en.wikipedia.org/wiki/

Histor of artif icial intelli ence  

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 4/22

     

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 5/22

Humankind has given itself the scientific name homo sapiens--man the

wise--because our mental capacities are so important to our everyday

lives and our sense of self. The field of artificial intelligence, or AI,

attempts to understand intelligent entities. Thus, one reason to study it is

to learn more about ourselves. But unlike philosophy and psychology,

which are also concerned with intelligence, AI strives to build  intelligent

entities as well as understand them. Another reason to study AI is that

these constructed intelligent entities are interesting and useful in their

own right. AI has produced many significant and impressive products

even at this early stage in its development. Although no one can predict

the future in detail, it is clear that computers with human-level

intelligence (or better) would have a huge impact on our everyday lives

and on the future course of civilization.

AI is one of the newest disciplines. It was formally initiated in 1956,

when the name was coined, although at that point work had been underway for about five years. Along with modern genetics, it is regularly

cited as the ``field I would most like to be in'' by scientists in other

disciplines. A student in physics might reasonably feel that all the good

ideas have already been taken by Galileo, Newton, Einstein, and the rest,

and that it takes many years of study before one can contribute new

ideas. AI, on the other hand, still has openings for a full-time Einstein.

AI currently encompasses a huge variety of subfields, from general-

purpose areas such as perception and logical reasoning, to specific tasks

such as playing chess, proving mathematical theorems, writing

poetry{poetry}, and diagnosing diseases. Often, scientists in other fields

move gradually into artificial intelligence, where they find the tools and

vocabulary to systematize and automate the intellectual tasks on which

they have been working all their lives. Similarly, workers in AI can

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 6/22

choose to apply their methods to any area of human intellectual

endeavor. In this sense, it is truly a universal field.

The study of intelligence is also one of the oldest disciplines. For over

2000 years, philosophers have tried to understand how seeing,

learning, remembering, and reasoning could, or should, be done. The

advent of usable computers in the early 1950s turned the learned but

armchair speculation concerning these mental faculties into a real

experimental and theoretical discipline. Many felt that the new

``Electronic Super-Brains'' had unlimited potential for intelligence.

``Faster Than Einstein'' was a typical headline. But as well as providing a

vehicle for creating artificially intelligent entities, the computer

provides a tool for testing theories of intelligence, and many theories

failed to withstand the test--a case of ``out of the armchair, into the

fire.''

What is AI? We have now explained why AI is exciting, but we have not said what it

is. We could just say, ``Well, it has to do with smart programs, so let's

get on and write some.'' But the history of science shows that it is

helpful to aim at the right goals. Early alchemists, looking for a potion

for eternal life and a method to turn lead into gold, were probably off 

on the wrong foot. Only when the aim changed, to that of finding

explicit theories that gave accurate predictions of the terrestrial world,

in the same way that early astronomy predicted the apparent motions

of the stars and planets, could the scientific method emerge and

productive science take place. Definitions of artificial intelligence

according to eight recent textbooks are shown in the table below.

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 7/22

These definitions vary along two main dimensions. The ones on top are

concerned with thought processes and reasoning, whereas the ones on

the bottom address behavior . Also, the definitions on the left measure

success in terms of human performance, whereas the ones on the rightmeasure against an ideal concept of intelligence, which we will call

rationality. A system is rational if it does the right thing.

Acting humanly: The Turing Test approach

The Turing Test, proposed by Alan Turing (Turing, 1950), was designed

to provide a satisfactory operational definition of intelligence. Turing

defined intelligent behavior as the ability to achieve human-level

performance in all cognitive tasks, sufficient to fool an interrogator.

Roughly speaking, the test he proposed is that the computer should be

interrogated by a human via a teletype, and passes the test if the

interrogator cannot tell if there is a computer or a human at the other

end. Chapter 26 discusses the details of the test, and whether or not a

computer is really intelligent if it passes.

The computer would need to possess the following capabilities:

  natural language processing to enable it to communicate

successfully in English (or some other human language);

  knowledge representation to store information provided before or

during the interrogation;

  automated reasoning to use the stored information to answer

questions and to draw new conclusions;

PROGRAMMING IN LOGIC

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 8/22

Logic programming is, in its broadest sense, the use of mathematical

logic for computer programming. In this view of logic programming,

which can be traced at least as far back as John McCarthy's [1958]

advice-taker proposal, logic is used as a purely declarative

representation language, and a theorem-prover or model-generator isused as the problem-solver. The problem-solving task is split between

the programmer, who is responsible only for ensuring the truth of 

programs expressed in logical form, and the theorem-prover or model-

generator, which is responsible for solving problems efficiently.

The programming language Prolog was developed in 1972 by Alain

Colmerauer. It emerged from a collaboration between Colmerauer in

Marseille and Robert Kowalski in Edinburgh. Colmerauer was workingon natural language understanding, using logic to represent semantics

and using resolution for question-answering. During the summer of 

1971, Colmerauer and Kowalski discovered that the clausal form of 

logic could be used to represent formal grammars and that resolution

theorem provers could be used for parsing. They observed that some

theorem provers, like hyper-resolution, behave as bottom-up parsers and

others, like SL-resolution (1971), behave as top-down parsers.

It was in the following summer of 1972, that Kowalski, again workingwith Colmerauer, developed the procedural interpretation of 

implications. This dual declarative/procedural interpretation later

became formalised in the Prolog notation

H :- B1, …, Bn. 

which can be read (and used) both declaratively and procedurally. It

also became clear that such clauses could be restricted to definite

clauses or Horn clauses, where H, B1, …, Bn are all atomic predicate

logic formulae, and that SL-resolution could be restricted (and

generalised) to LUSH or SLD-resolution. Kowalski's procedural

interpretation and LUSH were described in a 1973 memo, published

in 1974.

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 9/22

ABDUCTIVE LOGIC PROGRAMMING

Abductive Logic Programming is an extension of normal LogicProgramming that allows some predicates, declared as abducible

predicates, to be incompletely defined. Problem solving isachieved by deriving hypotheses expressed in terms of theabducible predicates as solutions of problems to be solved. Theseproblems can be either observations that need to be explained(as in classical abductive reasoning) or goals to be achieved (asin normal logic programming). It has been used to solveproblems in Diagnosis, Planning, Natural Language and MachineLearning.

Metalogic programming

Mathematical logic has a long tradition of distinguishing betweenobject language and metalanguage, logic programming alsoallows metalevel programming. The simplest metalogic progam isthe so-called "vanilla" meta-interpreter:

solve(true).

solve((A,B)):- solve(A),solve(B).

solve(A):- clause(A,B),solve(B).

Metalogic programming allows object-level and metalevel

representations to be combined, as in natural language. It can also be

used to implement any logic that is specified by means of inference

rules. 

Constraint logic programming

Constraint logic programming is an extension of normalLogic Programming that allows some predicates, declaredas constraint predicates, to occur as literals in the bodyof clauses. These literals are not solved by goal-reductionusing program clauses, but are added to a store of 

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 10/22

constraints, which is required to be consistent with somebuilt-in semantics of the constraint predicates.

Inductive logic programming

Inductive logic programming is concerned with generalizing positive

and negative examples in the context of background knowledge.

Generalizations, as well as the examples and background knowledge,

are expressed in logic programming syntax. Recent work in this area,

combining logic programming, learning and probability, has given riseto the new field of statistical relational learning and probabilistic

inductive logic programming. 

Linear logic programming

Basing logic programming within linear logic has resulted in thedesign of logic programming languages that are considerably

more expressive than those based on classical logic. Horn clauseprograms can only represent state change by the change inarguments to predicates. In linear logic programming, one canuse the ambient linear logic to support state change. Some earlydesigns of logic programming languages based on linear logicinclude LO [Andreoli & Pareschi, 1991], Lolli [Hodas & Miller,1994], ACL [Kobayashi & Yonezawa, 1994], and Forum [Miller,1996]. Forum provides a goal-directed interpretation of all of linear logic.

Lisp (programming language)

the second-oldest high-level programming language in widespread use today; only

Fortran is older (by one year). Like Fortran, Lisp has changed a great deal since its

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 11/22

early days, and a number of  dialects have existed over its history. Today,

the Lisp (or LISP) is a family of  computer programming languages with

a long history and a distinctive, fully parenthesized syntax. Originally

specified in 1958, Lisp is most widely known general-purpose Lisp

dialects are Common Lisp, Scheme, and Clojure. 

Lisp was originally created as a practical mathematical notation for

computer programs, influenced by the notation of  Alonzo Church's

lambda calculus. It quickly became the favored programming language

for artificial intelligence (AI) research. As one of the earliest

programming languages, Lisp pioneered many ideas in computer

science, including tree data structures, automatic storage management, 

dynamic typing, and the self-hosting compiler. 

The name  LISP derives from "LISt Processing". Linked lists are one of 

Lisp languages' major data structures, and Lisp source code is itself 

made up of lists. As a result, Lisp programs can manipulate source code

as a data structure, giving rise to the macro systems that allow

programmers to create new syntax or even new domain-specific

languages embedded in Lisp.

The interchangeability of code and data also gives Lisp its instantlyrecognizable syntax.

Lisp was first implemented by Steve Russell on an IBM 704 computer.

Russell had read McCarthy's paper, and realized (to McCarthy's

surprise) that the Lisp eval function could be implemented in machine

code.[3]

 The result was a working Lisp interpreter which could be used

to run Lisp programs, or more properly, 'evaluate Lisp expressions.'

The first complete Lisp compiler, written in Lisp, was implemented in

1962 by Tim Hart and Mike Levin at MIT.[5]

 This compiler introduced the

Lisp model of incremental compilation, in which compiled and

interpreted functions can intermix freely.

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 12/22

Connection to artificial intelligence

Since its inception, Lisp was closely connected with the artificialintelligence research community, especially on PDP-10  systems.

Lisp was used as the implementation of the programminglanguage Micro Planner which was used in the famous AI systemSHRDLU. In the 1970s, as AI research spawned commercialoffshoots, the performance of existing Lisp systems became agrowing issue.

Language innovations

Lisp was the first homoiconic programming language: the primary

representation of program code is the same type of list structurethat is also used for the main data structures. As a result, Lispfunctions can be manipulated, altered or even created within aLisp program without extensive parsing or manipulation of binarymachine code. This is generally considered one of the primaryadvantages of the language with regard to its expressive power,and makes the language amenable to metacircular evaluation. 

Virtual reality

The term virtual reality is sometimes used more generally to refer to any virtual world represented in a computer, even if it's just atext-based or graphical representation. 

Virtual reality (VR ) is a term that applies to computer-simulated environments that can simulate physical presence inplaces in the real world, as well as in imaginary worlds. Mostcurrent virtual reality environments are primarily visual

experiences, displayed either on a computer screen or throughspecial stereoscopic displays, but some simulations includeadditional sensory information, such as sound through speakersor headphones. Some advanced, haptic systems now includetactile information, generally known as force feedback, in medicaland gaming applications. 

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 13/22

 

Robotics - What is Robotics?

Roboticists develop man-made mechanical devices that can move by

themselves, whose motion must be modelled, planned, sensed, actuated

and controlled, and whose motion behaviour can be influenced by

“programming”. Robots are called “intelligent” if they succeed in moving

in safe interaction with an unstructured environment, while

autonomously achieving their specified tasks.

This definition implies that a device can only be called a “robot” if it

contains a movable mechanism, influenced by sensing, planning,

actuation and control components. It does not imply that a minimum

number of these components must be implemented in software, or be

changeable by the “consumer” who uses the device; for example, the

motion behaviour can have been hard-wired into the device by the

manufacturer.

Components of robotic systems 

This figure depicts the components that are part of all robotic

systems. The purpose of this Section is to describe the semantics of

the terminology used to classify the chapters in the WE Book:“sensing”, “planning”, “modelling”, “control”, etc.

The real robot is some mechanical device (“mechanism”) that moves

around in the environment, and, in doing so, physically interacts with

this environment. This interaction involves the exchange of physical

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 14/22

energy, in some form or another. Both the robot mechanism and the

environment can be the “cause” of the physical interaction through

“Actuation”, or experience the “effect” of the interaction, which can

be measured through “Sensing”.

Robotics as an integrated system of control interacting with the

physical world. 

Within the Controller component, several sub-activities are oftenidentified:

Modelling. The input-output relationships of all control components can

(but need not) be derived from information that is stored in a model.

This model can have many forms: analytical formulas, empirical look-up

tables, fuzzy rules, neural networks, etc. 

. The “Sensing model” and “Actuation model” contain the information

with which to transform raw physical data into task-dependentinformation for the controller, and vice versa.

The name “model” often gives rise to heated discussions among

different research “schools”, and the WEBook is not interested in

taking a stance in this debate: within the WEBook, “model” is to be

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 15/22

understood with its minimal semantics: “any information that is used to

determine or influence the input-output relationships of components in

the Controller.” 

Planning. This is the activity that predicts the outcome of potential

actions, and selects the “best” one. Almost by definition, planning can

only be done on the basis of some sort of model. 

Regulation. This component processes the outputs of the sensing and

planning components, to generate an actuation setpoint. Again, this

regulation activity could or could not rely on some sort of (system)

model.

The term “control” is often used instead of “regulation”, but it is

impossible to clearly identify the domains that use one term or the

other. The meaning used in the WEBook will be clear from the context.

Scales in robotic systems 

The above-mentioned “components” description of a robotic system is

to be complemented by a “scale” description, i.e., the following system

scales have a large influence on the specific content of the planning,

sensing, modelling and control components at one particular scale, and

hence also on the corresponding sections of the WEBook.

Mechanical scale. The physical volume of the robot determines to alarge extent the limites of what can be done with it. Roughly speaking,

a large-scale robot (such as an autonomous container crane or a space

shuttle) has different capabilities and control problems than a macro 

robot (such as an industrial robot arm), a desktop robot (such as those

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 16/22

“sumo” robots popular with hobbyists), or micro or nano robots.

Spatial scale. There are large differences between robots that act in

1D, 2D, 3D, or 6D (three positions and three orientations).

Time scale. There are large differences between robots that must

react within hours, seconds, milliseconds, or microseconds.

Power density scale. A robot must be actuated in order to move, but

actuators need space as well as energy, so the ratio between both

determines some capabilities of the robot.

System complexity scale. The complexity of a robot system increaseswith the number of interactions between independent sub-systems,

and the control components must adapt to this complexity.

Computational complexity scale. Robot controllers are inevitably

running on real-world computing hardware, so they are constrained by

the available number of computations, the available communication

bandwidth, and the available memory storage.

Background sensitivity 

Finally, no description of even scientific material is ever fully objective

or context-free, in the sense that it is very difficult for contributors

to the WE Book to “forget” their background when writing their

contribution. In this respect, robotics has, roughly speaking, two faces:

(i) the mathematical and engineering face, which is quite“standardized” in the sense that a large consensus exists about the

tools and theories to use (“systems theory”), and (ii) the AI face,

which is rather poorly standardized, not because of a lack of interest

or research efforts, but because of the inherent complexity of

“intelligent behaviour.” 

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 17/22

 

Neural Networks

•  These are Two Hot Research Areas in Artificial Intelligenceare:

Neural networks: Building a model of the brain and"training" that model to recognize certain types of patterns.

Genetic algorithms:   “Evolving" solutions to complex

problems (especially problems that are intractable using othermethods).

•  General brain architecture:o  Many (relatively) slow neurons, interconnected.o  Dendrites serve as input devices (receive electrical

impulses from other neurons)o  Cell body "sums" inputs from the dendrites (possibly

inhibiting or exciting)

o  If sum exceeds some threshold, the neuron fires anoutput impulse along axon.

ROBOTICS AND FUTURE

Robotics is the science and technology of ROBOTS. .

Researches are going on these days to implement thecomplete “Theories of Intelligence” and to make them capable for

tasks as Object Manipulation, Navigation, Mapping and Motion-Planning.

INTELLIGENT AND RATIONAL AGENT

•  An agent is anything that can be viewed as perceiving itsenvironment through sensors and acting upon that

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 18/22

environment through actuators, as Robotic agent:- camerasand infrared range finders for sensors.

•  The agent function maps from percept histories to actions:

Examples of Current

artificial intelligence:

Current AI:

Current AI AI in your everyday life Cars Self-parking Cruise control Speech

recognition Banks Monitoring for fraud Cell Phones Voice recognition

Internet Search Engines Safety Vision recognition for life-guarding Sports

Physical exams

Current AI:

Current AI Intelligent Homes Passive infrared sensors Temperature

sensors Water heating control Central heating control Magnetic door and

window contacts Electricity and light sensors.

Current AI:

Current AI Military-Unnamed aerial vehicles-Autonomous submersibles -Unmanned surveillance in shallow waters.

Current AI:

Current AI Medicine Computer enabled overlays (used during surgery)

Learning Retinal Implant System Hearing aids.

Current AI:

Current AI Toys 20Q (20 Questions ball) Roboraptor, Pleo and Rex Aibo

Lego Mindstorms Amazing Amanda doll.

Current AI:

Current AI Intelligent Games Computer Chess -explores huge numbers of 

potential future moves by both players but has taught us little about human-

like intelligence Herzog Zwei and Dune II -the first games to use AI, but

were very unsuccessful Battle Cruiser3000AD and Creatures -first to use

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 19/22

neural networks and emergent behavior Far Cry -exhibited very advanced

 AI for its time, although this made minor glitches more apparent Half- Life-

first combat oriented game to incorporate a significant amount of Artificial

Intelligence into its game play.

The Future of artificial intelligence.

FUTURE of AI:

FUTURE of AI Predicting the Future-Predicting the future is always a hit

and miss proposition, writes Kevin Anderson.

FUTURE of AI:

FUTURE of AI Gradual Change-Despite the rapid advance of technology,

the advent of strong AI will be a gradual process-"The road from here tothere is through thousands of these benign steps," said by Mr. Kurzweil,

author of two books on AI.

FUTURE of AI:

FUTURE of AI The Near Future-Right now, Dr Brooks says that artificial

intelligence is about at the same place the personal computer industry was

in 1978-In 1978, the Apple II was a year old and Atari had just introduced

the 400 and 800.

FUTURE of AI:

FUTURE of AI Jobs/Work-Even now we have Robots taking over jobs. -

Right now Japan uses about 320 robots of all sorts per 10,000 employees,

while Germany uses 148 industrial robots per 10,000 employees, Italy 116,

Sweden 99 and between 50 and 80 each in the United States.

FUTURE of AI:

FUTURE of AI The Chinese Room The Chinese Room argument makes

the claim that, if a machine acts intelligently then it has a "mind","understanding" and "conscious experience".

FUTURE of AI:

FUTURE of AI The Distant Future-“A.I. and Robots are running 40 years

behind computers,” said Dr Harvey-Although they are far behind it will only

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 20/22

be a matter of time before they become as regular as cell phones are in

your everyday life.

ADVANTAGES OF ARTIFICIAL INTELLIGENCE 

Artificial intelligence would not need any sleep. This would be an

advantage because it would not be interrupted from its tasks for sleep,

as well as other issues that plague biological minds like restroom breaks

and eating.

Un emotional consideration of problems. While an artificial mind could

theoretically have emotions, it would be better for performance if it

were programmed for unemotional reasoning. When people make

decisions, sometimes those decisions are based on emotion rather than

logic. This is not always the best way to make decisions.

Easier copying. Once an artificial mind is trained in a task, that mind can

then be copied very easily, compared to the training of multiple people

for the same task.

DISADVANTAGES OF ARTIFICIAL INTELLIGENCE

Limited sensory input. Compared to a biological mind, an artificial

mind is only capable of taking in a small amount of information.This is because of the need for individual input devices. The mostimportant input that we humans take in is the condition of ourbodies. Because we feel what is going on with our own bodies, wecan maintain them much more efficiently than an artificial mind.At this point, it is unclear whether that would be possible with acomputer system.

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 21/22

Importance of Artificial intelligence?

The importance of artificial intelligence is the ability tocreate a never-ending thought process and collective that

could solve our problems. Accomplishing this by thinkingof every possible solution. We are limited now by thenumber of people who can do this. With artificial

intelligence, we could build computers, upon thousandsof computers, that could all work in unison to solve ourgreat and most dire problems.

7/31/2019 Artificial Inteligence Hard Copy

http://slidepdf.com/reader/full/artificial-inteligence-hard-copy 22/22