TECHNICAL SEMINAR REPORT ON

ARTIFICIAL INTELLIGENCE
Submitted in partial fulfillment of the requirements
For the award of the degree
BACHELOR OF TECHNOLOGY
IN
ELECTRONICS & COMMUNICATION ENGINEERING

BY
G.Meghashyama Sarma (13R15A0401)

GEETHANJALI COLLEGE OF ENGINEERING AND TECHNOLOGY

Cheeryal (V), Keesara (M), R.R Dist, Hyderabad- 501 301
(Affliated to Jawaharlal Nehru Technological University, Hyderabad )
(2012-2016)
 CERTIFICATE

This is to certify that the seminar report entitled ARTIFICIAL

INTELLIGENCE submitted by G.Meghashyama Sarma (13R15A0401), department of
Electronics and Communication Engineering, in the partial fulfillment of the requirement for the
award of degree of Bachelor of Technology in Electronics and Communication Engineering as
specialization in Geethanjali college of Engineering and Technology, JNTU Hyderabad is a
record of bonafide work carried out under my guidance and supervision.

Dr.C.V.Narashimulu Dr. P. Srihari

Professor Professor
Internal guide. Head of the Department
 ACKNOWLEDGEMENT

The satisfaction and euphoria that accompany the successful completion of any task would be
incomplete without the mentioning of the people whose constant guidance and encouragement
made it possible. I take pleasure in presenting before you, my report, which is result of studied
blend of both research and knowledge.

I express our earnest gratitude to our internal guide Dr C.V.NARASHIMULU, professor, our
project guide, for his constant support, encouragement and guidance . I am grateful for his
cooperation and her valuable suggestions.

Lastly, we would thank our coordinator, MR. P. SUDHAKAR , professor, for giving me this
opportunity to present the technical report.

Above all, we are very much thankful to the management of Geethanjali College of
Engineering and Technology which was established by the high profiled intellectuals for the
cause of Technical Education in modern era, I wish that GCET sooner should become a deemed
university and produce uncountable young engineers and present them to the modern technical
world.

G.Meghashyama Sarma
(13R15A0401 )
 INDEX
Certificate
Acknowledgement

Contents Page No.

1.
 Abstract
The term artificial intelligence is used to describe a property of machines or programs: the
intelligence that the system demonstrates. Among the traits that researchers hope machines will
exhibit are reasoning, knowledge, planning, learning, communication, perception and the ability
to move and manipulate objects.

Constructing robots that perform intelligent tasks has always been a highly motivating factor for
the science and technology of information processing. Unlike philosophy and psychology, which
are also concerned with intelligence, AI strives to build intelligent entities such as robots as well
as understand them. 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.

Neural Networks have been proposed as an alternative to Symbolic Artificial Intelligence in

constructing intelligent systems. They are motivated by computation in the brain. Small
Threshold computing elements when put together produce powerful information processing
machines. In this report, we put forth the foundational ideas in artificial intelligence and
important concepts in Search Techniques, Knowledge Representation, Language Understanding,
Machine Learning, Neural Computing and such other disciplines.

AI combined with various techniques in neural networks, fuzzy logic and natural language
processing will be able to revolutionize the future of machines and it will transform the
mechanical devices helping humans into intelligent rational robots having emotions.
 1. INTRODUCTION

Artificial Intelligence (AI) is the branch of computer science which deals with intelligence of
machines where an intelligent agent is a system that perceives its environment and takes actions
which maximize its chances of success. It is the study of ideas which enable computers to do the
things that make people seem intelligent. The central principles of AI include such traits as
reasoning, knowledge, planning, learning, communication, perception and the ability to move
and manipulate objects. It is the science and engineering of making intelligent machines,
especially intelligent computer programs.

1.1 ARTIFICIAL INTELLIGENCE METHODS:

At the present time, AI methods can be divided into two broad categories: (a) symbolic AI,
which focuses on the development of knowledge-based systems (KBS); and (b) computational
intelligence, which includes such methods as neural networks (NN), fuzzy systems (FS), and
evolutionary computing. A very brief introduction to these AI methods is given below, and each
method is discussed in more detail in the different sections of this circular.

Knowledge-Based Systems:
A KBS can be defined as a computer system capable of giving advice in a particular domain,
utilizing knowledge provided by a human expert. A distinguishing feature of KBS lies in the
separation behind the knowledge, which can be represented in a number of ways such as rules,
frames, or cases, and the inference engine or algorithm which uses the knowledge base to arrive
at a conclusion.

Neural Networks:
NNs are biologically inspired systems consisting of a massively connected network of
computational neurons, organized in layers. By adjusting the weights of the network, NNs can

1
be trained to approximate virtually any nonlinear function to a required degree of accuracy.
NNs typically are provided with a set of input and output exemplars. A learning algorithm (such
as back propagation) would then be used to adjust the weights in the network so that the network
would give the desired output, in a type of learning commonly called supervised learning.

Fuzzy Logic Systems:

Fuzzy set theory was proposed by Zadeh (1965) as a way to deal with the ambiguity associated
with almost all real-world problems. Fuzzy set membership functions provide a way to show that
an object can partially belong to a group. Classic set theory defines sharp boundaries between
sets, which mean that an object can only be a member or a nonmember of a given set. Fuzzy
membership functions allow for gradual transitions between sets and varying degrees of
membership for objects within sets. Complete membership in a fuzzy function is indicated by a
value of +1, while complete non-membership is shown by a value of 0. Partial membership is
represented by a value between 0 and +1.

1.2. DEFNITIONS OF AI:

Computers with the ability to mimic or duplicate the functions of the human brain
Artificial Intelligence (AI) is the study of how computer systems can simulate intelligent
processes such as learning, reasoning, and understanding symbolic information in
context. AI is inherently a multi-disciplinary field. Although it is most commonly viewed
as a subfield of computer science, and draws upon work in algorithms, databases, and
theoretical computer science, AI also has close connections to the neurosciences,
cognitive science and cognitive psychology, mathematical logic, and engineering."
``The exciting new effort to make computers think ... machines with minds, in the full
and literal sense'' (Haugeland, 1985)
``The automation of activities that we associate with human thinking, activities such as
decision-making, problem solving, learning ...'' (Bellman, 1978) ``The study of mental
faculties through the use of computational models'' (Charniak and McDermott, 1985)
``The study of the computations that make it possible to perceive, reason, and act''
(Winston, 1992)

2
 ``The art of creating machines that perform functions that require intelligence when
performed by people'' (Kurzweil, 1990)
``The study of how to make computers do things at which, at the moment, people are
better'' (Rich and Knight, 1991) ``A field of study that seeks to explain and emulate
intelligent behavior in terms of computational processes'' (Schalkoff, 1990)
``The branch of computer science that is concerned with the automation of intelligent
behavior'' (Luger and Stubblefield, 1993)
"Artificial intelligence is the study of ideas to bring into being machines that respond to
stimulation consistent with traditional responses from humans, given the human capacity
for contemplation, judgment and intention. Each such machine should engage in critical
appraisal and selection of differing opinions within itself. Produced by human skill and
labor, these machines should conduct themselves in agreement with life, spirit and
sensitivity, though in reality, they are imitations.

2. HISTORY

3
 The intellectual roots of AI, and the concept of intelligent machines, may be found in
Greek mythology. Intelligent artifacts appear in literature since then, with real mechanical
devices actually demonstrating behavior with some degree of intelligence. After modern
computers became available following World War-II, it has become possible to create programs
that perform difficult intellectual tasks.

1950 - 1960:-

The first working AI programs were written in 1951 to run on the Ferranti Mark I
machine of the University of Manchester (UK): a draughts-playing program written by
Christopher Strachey and a chess-playing program written by Dietrich Prinz.

1960 1970 :-

During the 1960s and 1970s Marvin Minsky and Seymour Papert publish Perceptrons,
demonstrating limits of simple neural networks and Alain Colmerauer developed the Prolog
computer language. Ted Shortliffe demonstrated the power of rule-based systems for knowledge
representation and inference in medical diagnosis and therapy in what is sometimes called the
first expert system. Hans Moravec developed the first computer-controlled vehicle to
autonomously negotiate cluttered obstacle courses.

1980s ONWARDS :-

In the 1980s, neural networks became widely used with the back propagation algorithm,
first described by Paul John Werbos in 1974. The 1990s marked major achievements in many
areas of AI and demonstrations of various applications. Most notably Deep Blue, a chess-playing
computer, beat Garry Kasparov in a famous six-game match in 1997.

The modern history of AI can be traced back to the year 1956 when John McCarthy proposed the
term as the topic for a conference held at Dartmouth College in New Hampshire devoted to the

4
subject. The initial goals for the field were too ambitious and the first few AI systems failed to
deliver what was promised. After a few of these early failures, AI researchers started setting
some more realistic goals for themselves. In the 1960s and the 1970s, the focus of AI research
was primarily on the development of KBS or expert systems. During these years, expert systems
technology were applied to a wide range of problems and fields ranging from medical diagnosis
to inferring molecular structure to natural language understanding. The same period also
witnessed early work on NNs, which showed how a distributed structure of elements could
collectively represent an individual concept, with the added advantage of robustness and
parallelism. However, the publication of Minsk and Papers book Perceptrons in 1969, which
argued for the limited representation capabilities of NN, led to the demise of NN research in the
1970s.

The late 1980s and the 1990s saw a renewed interest in NN research when several
different researchers reinvented the back propagation learning algorithm (although the algorithm
was really first discovered in 1969). The back propagation algorithm was soon applied to many
learning problems causing great excitement within the AI community. The 1990s also witnessed
some dramatic changes in the content and methodology of AI research. The focus of the field has
been shifting toward grounding AI methods on a rigorous mathematical foundation, as well as to
tackle real-world problems and not just toy examples. There is also a move toward the
development of hybrid intelligent systems (i.e., systems that use more than one AI method)
stemming from the recognition that many AI methods are complementary. Hybrid intelligent
systems also started to use newer paradigms that mimic biological behavior such as GAs and
fuzzy logic.

3. CATEGORIES OF AI

5
 AI divides roughly into two schools of thought:

Conventional AI.
Computational Intelligence (CI).

1. Conventional AI :-

Conventional AI mostly involves methods now classified as machine learning,

characterized by formalism and statistical analysis. This is also known as symbolic AI, logical
AI, neat AI and Good Old Fashioned Artificial Intelligence (GOFAI).

Methods include:

Expert systems: apply reasoning capabilities to reach a conclusion. An expert system can
process large amounts of known information and provide conclusions based on them.
Case based reasoning
Bayesian networks
Behavior based AI: a modular method of building AI systems by hand.

2. Computational Intelligence (CI) :-

Computational Intelligence involves iterative development or learning (e.g. parameter

tuning e.g. in connectionist systems). Learning is based on empirical data and is associated with
non-symbolic AI, scruffy AI and soft computing.

Methods include:

Neural networks: systems with very strong pattern recognition

capabilities.
Fuzzy systems: techniques for reasoning under uncertainty, has been widely used in
modern industrial and consumer product control systems.

6
 Evolutionary computation: applies biologically inspired concepts such as populations,
mutation and survival of the fittest to generate increasingly better solutions to the problem. These
methods most notably divide into evolutionary algorithms (e.g. genetic algorithms) and swarm
intelligence (e.g. ant algorithms).

4. APPLCATIONS OF AI

7
4.1 Finance:

Banks use artificial intelligence systems to organize operations, invest in stocks, and manage
properties. In August 2001, robots beat humans in a simulated financial trading competition.
Financial institutions have long used artificial neural network systems to detect charges or claims
outside of the norm, flagging these for human investigation. Some other applications in this
section include loan investigation, ATM design, safe and fast banking etc.

4.2 Medicine:

A medical clinic can use artificial intelligence systems to organize bed schedules, make a staff
rotation, and provide medical information. Artificial neural networks are used for medical
diagnosis, functioning as Machine differential diagnosis. AI has also application in fields
of cardiology (CRG), neurology (MRI), embryology (sonography), complex operations of
internal organs etc.

4.3 Heavy Industry:

Now a days in big industries all the work and machine operations are controlled by principles of
Artificial Intelligence. These huge machines involve risk in their manual maintenance and
working. So in becomes necessary part to have an efficient and safe operation agent in their
operation.

4.3.1 Application Types and Situations: Intelligent software systems play a number of roles in
heavy industry. Selected examples are discussed below.

PROCESS CONTROL: These tasks usually involve automation of low-level control in a real-
time system. The implemented systems are concerned with fault detection, diagnosis and
alarming, and with operating the control devices in the control loops. Integral functions of
intelligent software are sensor diagnostics, handling of erroneous or missing data, and
performing temporal reasoning.

8
PROCESS MONITORING: Artificial Intelligence systems monitor, compare and analyze the
process behavior of events that are crucial to successful operation and suggest any corrective
action that should be implemented by the operators.

FAULT DIAGNOSIS AND MAINTAINANCE: It is practically impossible to diagnose huge

machines regularly and precisely. Working of faulty machines may cause great loss to the
industry. So, Artificial Intelligence systems offer a number of advantages for working with
diagnostic problems. First, they can monitor and analyze hundreds of sensors, determine any
anomalies in their functions and identify probable causes of the discrepancies between expected
and actual operating conditions.

SCHEDULING AND PLANNING: In the present day world TIME ELEMENT plays an
important role. So, completion of manufacturing within short period of time in addition to good
quality becomes very important. Intelligent software offers several advantages in developing
computerized scheduling systems. Instead of presenting one optimization schedule, AI-based
scheduling systems present several schedules with their evaluation indexes. The operator can
then select the "best" optimum schedule.

4.4 Telecommunications:

Many telecommunications companies make use of heuristic search in the management of their
workforces, for example BT Group has deployed heuristic search in a scheduling application that
provides the work schedules of 20000 engineers.

4.5 Music:

AI, scientists are trying to make the computer emulate the activities of the skillful musician.
Composition, performance, music theory, sound processing are some of the major areas on which
research in Music and Artificial Intelligence are focusing on. Some of them are

Orchestra: This program was designed to provide small-budget productions with instrumentation
for all instruments usually present in the full-fledged orchestra.

9
COMPUTER ACCOMPNIMENT: The Computer Music Project at CMU develops computer
music and interactive performance technology to enhance human musical experience and
creativity.

SMART MUSIC: Smart Music is an interactive, computer-based practice tool for musicians.
CHUCK: Chuck is a text-based, cross-platform language that allows real-time synthesis,
composition, performance and analysis of music.

4.6 Antivirus:
Artificial intelligence (AI) techniques have played increasingly important role in antivirus
detection. At present, some principal artificial intelligence techniques applied in antivirus
detection are proposed, including heuristic technique, data mining, agent technique, artificial
immune, and artificial neural network. It improves the performance of antivirus detection
systems, and promotes the production of new artificial intelligence algorithm and the application
in antivirus detection to integrate antivirus detection with artificial intelligence. This paper
introduces the main artificial intelligence technologies, which have been applied in antivirus
system. Meanwhile, it also points out a fact that combining all kinds of artificial intelligence
technologies will become the main development trend in the field of antivirus.

4.7 Robotics:

Definition: What is a Robot?

Robots are physical agents that perform tasks by manipulating the physical world. They are
equipped with sensors to perceive their environment and effectors to assert physical forces on it

10
(covered in more detail in next section). Robots can be put into three main categories:
manipulators, mobile robots and humanoid.
Robotics and AI
Artificial intelligence is a theory. The base object is the agent who is the "actor". It is realized in
software. Robots are manufactured as hardware. The connection between those two is that the
control of the robot is a software agent that reads data from the sensors decides what to do next
and then directs the effectors to act in the physical world.

Robot application software

Most robot manufacturers keep their software hidden. It

is impossible to find out how most robots are programmed. It
is almost as if they had no software in many cases.
Regardless which language is used, the end result of
robot software is to create robotic applications that help or
entertain people. Applications include command-and-control
and tasking software. Command-and-control software includes robot control GUIs for tele-
operated robots, point-n-click command software for autonomous robots, and scheduling
software for mobile robots in factories. Tasking software includes simple drag-n-drop interfaces
for setting up delivery routes, security patrols and visitor tours; it also includes custom programs
written to deploy specific applications. General-purpose robot application software is deployed
on widely distributed robotic platforms.

4.8 Gaming:

11
In the earlier days gaming technology was not broadened. Physicist Willy Higginbotham created
the first video game in 1958. It was called Tennis For Two and was plan oscilloscope. But now
AI technology has become vast and standard has also been increased. Developers are designing
more realistic, heavily graphical, 3-D games. Some of most popular games of present day are
Crisis, Fear, Fall Out, Halo etc.

Other fields in which AI methods are implemented :-

Automation.
Cybernetics.
Hybrid intelligent system.
Intelligent agent.
Intelligent control.
Automated reasoning.
Data mining.
Behavior-based robotics.
Cognitive robotics.
Developmental robotics.
Evolutionary robotics.
Chatbot.
Credit granting.
Information management and retrieval.
AI and expert systems embedded in products.
Help desks and assistance.

12
 Employee performance evaluation.
Shipping.
Marketing.
Warehouse optimization.
In space workstation maintenance.
Satellite controls.
Network developments.
Military activity controls.
Nuclear management.

4.9 Speech Recognition:

In the 1990s, computer speech recognition reached a practical level for limited purposes. Thus
United Airlines has replaced its keyboard tree for flight information by a system using speech
recognition of flight numbers and city names. It is quite convenient. On the other hand, while it
is possible to instruct some computers using speech, most users have gone back to the keyboard
and the mouse as still more convenient.

4.10 Understanding Natural Language:

Just getting a sequence of words into a computer is not enough. Parsing sentences is not enough
either. The computer has to be provided with an understanding of the domain the text is about,
and this is presently possible only for very limited domains.

4.11 Computer Vision:

The world is composed of three-dimensional objects, but the inputs to the human eye and
computers TV cameras are two dimensional. Some useful programs can work solely in two
dimensions, but full computer vision requires partial three-dimensional information that is not
just a set of two-dimensional views. At present there are only limited ways of representing three-
dimensional information directly, and they are not as good as what humans evidently use.

4.12 Expert Systems:

A ``knowledge engineer'' interviews experts in a certain domain and tries to embody their
knowledge in a computer program for carrying out some task. How well this works depends on
whether the intellectual mechanisms required for the task are within the present state of AI. One

13
of the first expert systems was MYCIN in 1974, which diagnosed bacterial infections of the
blood and suggested treatments. It did better than medical students or practicing doctors,
provided its limitations were observed.

4.13 Heuristic Classification:

One of the most feasible kinds of expert system given the present knowledge of AI is to put some
information in one of a fixed set of categories using several sources of information. An example is
advising whether to accept a proposed credit card purchase. Information is available about the owner of
the credit card, his record of payment and also about the item he is buying and about the establishment
from which he is buying it (e.g., about whether there have been previous credit card frauds at this
establishment).

5. ARTIFICIAL NEURAL NETWORKS

In machine learning and cognitive science, artificial neural networks (ANNs) are a family of
models inspired by biological neural networks (the central nervous systems of animals, in
particular the brain) and are used to estimate or approximate functions that can depend on a large
number of inputs and are generally unknown. Artificial neural networks are generally presented
as systems of interconnected "neurons" which exchange messages between each other. The
connections have numeric weights that can be tuned based on experience, making neural nets
adaptive to inputs and capable of learning.

For example, a neural network for handwriting recognition is defined by a set of input neurons
which may be activated by the pixels of an input image. After being weighted and transformed
by a function (determined by the network's designer), the activations of these neurons are then

14
passed on to other neurons. This process is repeated until finally, an output neuron is activated.
This determines which character was read.

Like other machine learning methods systems that learn from data neural networks have been
used to solve a wide variety of tasks that are hard to solve using ordinary rule-based
programming, including computer vision and speech recognition.

15
An artificial neural network is an interconnected group of nodes, akin to the vast network
of neurons in a brain. Here, each circular node represents an artificial neuron and an arrow
represents a connection from the output of one neuron to the input of another.

5.2 Background Of Neural Networks:

Examinations of humans' central nervous systems inspired the concept of artificial neural
networks. In an artificial neural network, simple artificial nodes, known as "neurons",
"neurodes", "processing elements" or "units", are connected together to form a network which
mimics a biological neural network.

There is no single formal definition of what an artificial neural network is. However, a class of
statistical models may commonly be called "neural" if it possesses the following characteristics:

16
 1. contains sets of adaptive weights, i.e. numerical parameters that are tuned by a
learning algorithm, and
2. capability of approximating non-linear functions of their inputs.

The adaptive weights can be thought of as connection strengths between neurons, which are
activated during training and prediction.

Neural networks are similar to biological neural networks in the performing of functions
collectively and in parallel by the units, rather than there being a clear delineation of subtasks to
which individual units are assigned. The term "neural network" usually refers to models
employed in statistics, cognitive psychology and artificial intelligence. Neural network models,
which command the central nervous system and the rest of the brain, are part of theoretical
neuroscience and computational neuroscience[1]

In modern software implementations of artificial neural networks, the approach inspired by

biology has been largely abandoned for a more practical approach based on statistics and signal
processing. In some of these systems, neural networks or parts of neural networks (like artificial
neurons) form components in larger systems that combine both adaptive and non-adaptive
elements. While the more general approach of such systems is more suitable for real-world
problem solving, it has little to do with the traditional, artificial intelligence connectionist
models. What they do have in common, however, is the principle of non-linear, distributed,
parallel and local processing and adaptation. Historically, the use of neural network models
marked a directional shift in the late eighties from high-level (symbolic) artificial intelligence,
characterized by expert systems with knowledge embodied in if-then rules, to low-level (sub-
symbolic) machine learning, characterized by knowledge embodied in the parameters of
a dynamical system.

5.3 History Of Neural Networks:

Warren McCulloch and Walter Pitts created a computational model for neural networks based on
mathematics and algorithms called threshold logic. This model paved the way for neural network
research to split into two distinct approaches. One approach focused on biological processes in
the brain and the other focused on the application of neural networks to artificial intelligence.

17
Hebbian Learning:
In the late 1940s psychologist Donald Hebb created a hypothesis of learning based on the
mechanism of neural plasticity that is now known as Hebbian learning. Hebbian learning is
considered to be a 'typical' unsupervised learning rule and its later variants were early models for
long term potentiation. Researchers started applying these ideas to computational models in 1948
with Turing's B-type machines.

Farley and Wesley A. Clark first used computational machines, then called "calculators," to
simulate a Hebbian network at MIT. Other neural network computational machines were created
by Rochester, Holland, Habit, and Duda.

Frank Rosenblatt created the perceptron, an algorithm for pattern recognition based on a two-
layer computer learning network using simple addition and subtraction. With mathematical
notation, Rosenblatt also described circuitry not in the basic perceptron, such as the exclusive-or
circuit, a circuit which could not be processed by neural networks until after the back
propagation algorithm was created by Paul Werbos.

Neural network research stagnated after the publication of machine learning research by Marvin
Minsky and Seymour Papert, who discovered two key issues with the computational machines
that processed neural networks. The first was that basic perceptrons were incapable of processing
the exclusive-or circuit. The second significant issue was that computers didn't have enough
processing power to effectively handle the long run time required by large neural networks.
Neural network research slowed until computers achieved greater processing power.

Back Propagation and Resurgence:

A key advance that came later was the back propagation algorithm which effectively solved the
exclusive-or problem, and more generally the problem of quickly training multi-layer neural
networks.

18
In the mid-1980s, parallel distributed processing became popular under the name connectionism.
The textbook by David E. Rumelhart and James McClelland provided a full exposition of the use
of connectionism in computers to simulate neural processes.

Neural networks, as used in artificial intelligence, have traditionally been viewed as simplified
models of neural processing in the brain, even though the relation between this model and the
biological architecture of the brain is debated; it's not clear to what degree artificial neural
networks mirror brain function.

Support vector machines and other, much simpler methods such as linear classifiers gradually
overtook neural networks in machine learning popularity. But the advent of deep learning in the
late 2000s sparked renewed interest in neural nets.

Improvements since 2006:

Computational devices have been created in CMOS, for both biophysical simulation and
neuromorphic computing. More recent efforts show promise for creating Nano devices for very
large scale principal components analyses and convolution. If successful, these efforts could
usher in a new era of neural computing that is a step beyond digital computing, because it
depends on learning rather than programming and because it is fundamentally analog rather than
digital even though the first instantiations may in fact be with CMOS digital devices.

Between 2009 and 2012, the recurrent neural networks and deep feedforward neural networks
developed in the research group of Jrgen Schmidhuber at the Swiss AI Lab IDSIA have won
eight international competitions in pattern recognition and machine learning. For example, the
bi-directional and multi-dimensional long short term memory (LSTM) of Alex Graves et al. won
three competitions in connected handwriting recognition at the 2009 International Conference on
Document Analysis and Recognition (ICDAR), without any prior knowledge about the three
different languages to be learned.

Fast GPU-based implementations of this approach by Dan Ciresan and colleagues at IDSIA have
won several pattern recognition contests, including the IJCNN 2011 Traffic Sign Recognition

19
Competition, the ISBI 2012 Segmentation of Neuronal Structures in Electron Microscopy Stacks
challenge, and others. Their neural networks also were the first artificial pattern recognizers to
achieve human-competitive or even superhuman performance on important benchmarks such as
traffic sign recognition (IJCNN 2012), or the MNIST handwritten digits problem of Yann LeCun
at NYU.

Deep, highly nonlinear neural architectures similar to the 1980 neocognitron by Kunihiko
Fukushima and the "standard architecture of vision", inspired by the simple and complex cells
identified by David H. Hubel and Torsten Wiesel in the primary visual cortex, can also be pre-
trained by unsupervised methods of Geoff Hinton's lab at University of Toronto. A team from
this lab won a 2012 contest sponsored by Merck to design software to help find molecules that
might lead to new drugs.

5.4 Types Of Neural Networks:

1. Feed forward neural network
2. Radial basis function (RBF) network
3. Recurrent neural network
4. Fully recurrent network
5. Hopfield network
6. Boltzmann machine
7. Simple recurrent networks
8. Long short-term memory network
9. Bi-directional RNN
10. Hierarchical RNN
11. Stochastic neural networks
12. Modular neural networks
13. Committee of machines
14. Associative neural network (ASNN)
15. Physical neural network

20
5.5 Properties Of Neural Networks:

Computational power:
The multilayer perceptron is a universal function approximator, as proven by the universal
approximation theorem. However, the proof is not constructive regarding the number of neurons
required or the settings of the weights.
Work by Hava Siegelmann and Eduardo D. Sontag has provided a proof that a specific recurrent
architecture with rational valued weights (as opposed to full precision real number-valued
weights) has the full power of a Universal Turing Machine using a finite number of neurons and
standard linear connections. Further, it has been shown that the use of irrational values for
weights results in a machine with super-Turing power.

Capacity:
Artificial neural network models have a property called 'capacity', which roughly corresponds to
their ability to model any given function. It is related to the amount of information that can be
stored in the network and to the notion of complexity.

Convergence:
Nothing can be said in general about convergence since it depends on a number of factors.
Firstly, there may exist many local minima. This depends on the cost function and the model.
Secondly, the optimization method used might not be guaranteed to converge when far away
from a local minimum. Thirdly, for a very large amount of data or parameters, some methods
become impractical. In general, it has been found that theoretical guarantees regarding
convergence are an unreliable guide to practical application.

Generalization and statistics:

In applications where the goal is to create a system that generalizes well in unseen examples, the
problem of over-training has emerged. This arises in convoluted or over-specified systems when
the capacity of the network significantly exceeds the needed free parameters. There are two
schools of thought for avoiding this problem: The first is to use cross-validation and similar
techniques to check for the presence of overtraining and optimally select hyper parameters such
as to minimize the generalization error. The second is to use some form of regularization. This is
a concept that emerges naturally in a probabilistic (Bayesian) framework, where the
regularization can be performed by selecting a larger prior probability over simpler models; but
also in statistical learning theory, where the goal is to minimize over two quantities: the

21
'empirical risk' and the 'structural risk', which roughly corresponds to the error over the training
set and the predicted error in unseen data due to over fitting.

Confidence analysis of a neural network

Supervised neural networks that use a mean squared error (MSE) cost function can use formal
statistical methods to determine the confidence of the trained model. The MSE on a validation
set can be used as an estimate for variance. This value can then be used to calculate
the confidence interval of the output of the network, assuming a normal distribution. A
confidence analysis made this way is statistically valid as long as the output distribution stays the
same and the network is not modified.
By assigning a softmax activation function, a generalization of the logistic function, on the
output layer of the neural network (or a softmax component in a component-based neural
network) for categorical target variables, the outputs can be interpreted as posterior probabilities.
This is very useful in classification as it gives a certainty measure on classifications.

5.6 Problems Associated With Neural Networks:

Training issues:
A common criticism of neural networks, particularly in robotics, is that they require a large
diversity of training for real-world operation. This is not surprising, since any learning machine
needs sufficient representative examples in order to capture the underlying structure that allows it
to generalize to new cases. Dean A. Pomerleau, in his research presented in the paper
"Knowledge-based Training of Artificial Neural Networks for Autonomous Robot Driving," uses
a neural network to train a robotic vehicle to drive on multiple types of roads (single lane, multi-
lane, dirt, etc.). A large amount of his research is devoted to (1) extrapolating multiple training
scenarios from a single training experience, and (2) preserving past training diversity so that the

22
system does not become overtrained (if, for example, it is presented with a series of right turn it
should not learn to always turn right). These issues are common in neural networks that must
decide from amongst a wide variety of responses, but can be dealt with in several ways, for
example by randomly shuffling the training examples, by using a numerical optimization
algorithm that does not take too large steps when changing the network connections following an
example, or by grouping examples in so-called mini-batches.
K. Dewdney, a former Scientific American columnist, wrote in 1997, "Although neural nets do
solve a few toy problems, their powers of computation are so limited that I am surprised anyone
takes them seriously as a general problem-solving tool."

Hardware issues:

To implement large and effective software neural networks, considerable processing and storage
resources need to be committed.[56] While the brain has hardware tailored to the task of
processing signals through a graph of neurons, simulating even a most simplified form on von
Neumann architecture may compel a neural network designer to fill many millions
of database rows for its connections which can consume vast amounts of
computer memory and hard disk space. Furthermore, the designer of neural network systems will
often need to simulate the transmission of signals through many of these connections and their
associated neurons which must often be matched with incredible amounts of CPU processing
power and time.
Jrgen Schmidhuber notes that the resurgence of neural networks in the twenty-first century, and
their renewed success at image recognition tasks is largely attributable to advances in hardware:
from 1991 to 2015, computing power, especially as delivered by GPGPUs (on GPUs), has
increased around a million-fold, making the standard backpropagation algorithm feasible for
training networks that are several layers deeper than before (but adds that this doesn't overcome
algorithmic problems such as vanishing gradients "in a fundamental way").[57] The use of GPUs
instead of ordinary CPUs can bring training times for some networks down from months to mere
days.[56]
Computing power continues to grow roughly according to Moore's Law, which may provide
sufficient resources to accomplish new tasks. Neuromorphic engineering addresses the hardware
difficulty directly, by constructing non-von-Neumann chips with circuits designed to implement
neural nets from the ground up.

23
Practical counterexamples to criticisms:
Arguments against Dewdney's position are that neural networks have been successfully used to
solve many complex and diverse tasks, ranging from autonomously flying aircraft [58] to detecting
credit card fraud.
Technology writer Roger Bridgman commented on Dewdney's statements about neural nets:
Neural networks, for instance, are in the dock not only because they have been hyped to high
heaven, (what hasn't?) but also because you could create a successful net without understanding
how it worked: the bunch of numbers that captures its behavior would in all probability be "an
opaque, unreadable table...valueless as a scientific resource".
In spite of his emphatic declaration that science is not technology, Dewdney seems here to
pillory neural nets as bad science when most of those devising them are just trying to be good
engineers. An unreadable table that a useful machine could read would still be well worth
having.
Although it is true that analyzing what has been learned by an artificial neural network is
difficult, it is much easier to do so than to analyze what has been learned by a biological neural
network. Furthermore, researchers involved in exploring learning algorithms for neural networks
are gradually uncovering generic principles which allow a learning machine to be successful. For
example, Bengio and LeCun (2007) wrote an article regarding local vs non-local learning, as
well as shallow vs deep architecture.

5.7 Neural Network Software:

Neural network software is used to simulate, research, develop, and apply artificial neural
networks, software concepts adapted from biological neural networks, and, in some cases, a
wider array of adaptive systems such as artificial intelligence and machine learning.

Simulators:
Neural network simulators are software applications that are used to simulate the behavior of
artificial or biological neural networks. They focus on one or a limited number of specific types
of neural networks. They are typically stand-alone and not intended to produce general neural
networks that can be integrated in other software. Simulators usually have some form of built-in

24
visualization to monitor the training process. Some simulators also visualize the physical
structure of the neural network.

1. Research simulators:

SNNS research neural network simulator

Historically, the most common type of neural network software was intended for researching
neural network structures and algorithms. The primary purpose of this type of software is,
through simulation, to gain a better understanding of the behavior and properties of neural
networks. Today in the study of artificial neural networks, simulators have largely been replaced
by more general component based development environments as research platforms.

Commonly used artificial neural network simulators include the Stuttgart Neural Network
Simulator (SNNS), Emergent, Neural Lab.

In the study of biological neural networks however, simulation software is still the only available
approach. In such simulators the physical biological and chemical properties of neural tissue, as
well as the electromagnetic impulses between the neurons are studied.

Commonly used biological network simulators include Neuron, GENESIS, NEST and Brian.

2. Data analysis simulators:

Unlike the research simulators, the data analysis simulators are intended for practical
applications of artificial neural networks. Their primary focus is on data mining and forecasting.
Data analysis simulators usually have some form of preprocessing capabilities. Unlike the more
general development environments data analysis simulators use a relatively simple static neural
network that can be configured. A majority of the data analysis simulators on the market use
backpropagating networks or self-organizing maps as their core. The advantage of this type of
software is that it is relatively easy to use.

25
3. Simulators for teaching neural network theory:
When the Parallel Distributed Processing volumes[1] [2][3] were released in 1986-87, they
provided some relatively simple software. The original PDP software did not require any
programming skills, which led to its adoption by a wide variety of researchers in diverse fields.
The original PDP software was developed into a more powerful package called PDP++, which in
turn has become an even more powerful platform called Emergent. With each development, the
software has become more powerful, but also more daunting for use by beginners.

In 1997, the tLearn software was released to accompany a book.[4] This was a return to the idea
of providing a small, user-friendly, simulator that was designed with the novice in mind. tLearn
allowed basic feed forward networks, along with simple recurrent networks, both of which can
be trained by the simple back propagation algorithm. tLearn has not been updated since 1999.

In 2011, the Basic Prop simulator was released. Basic Prop is a self-contained application,
distributed as a platform neutral JAR file, that provides much of the same simple functionality as
tLearn.

5.8 Advantages And Disadvantages Of Neural Networks:

Advantages Of Neural Networks:

Neural networks, with their remarkable ability to derive meaning from complicated or imprecise
data, can be used to extract patterns and detect trends that are too complex to be noticed by either
humans or other computer techniques. A trained neural network can be thought of as an "expert"
in the category of information it has been given to analyze. This expert can then be used to
provide projections given new situations of interest and answer "what if" questions.
Other advantages include:

1. Adaptive learning: An ability to learn how to do tasks based on the data given for
training or initial experience.

26
 2. Self-Organization: An ANN can create its own organization or representation of the
information it receives during learning time.
3. Real Time Operation: ANN computations may be carried out in parallel, and special
hardware devices are being designed and manufactured which take advantage of this
capability.
4. Fault Tolerance via Redundant Information Coding: Partial destruction of a network
leads to the corresponding degradation of performance. However, some network
capabilities may be retained even with major network damage.

Disadvantages Of Neural Networks:

The major issues of concern today are the scalability problem, testing, verification, and
integration of neural network systems into the modern environment. Neural network programs
sometimes become unstable when applied to larger problems. The defense, nuclear and space
industries are concerned about the issue of testing and verification. The mathematical theories
used to guarantee the performance of an applied neural network are still under development. The
solution for the time being may be to train and test these intelligent systems much as we do for
humans. Also there are some more practical problems like:

1. The operational problem encountered when attempting to simulate the parallelism of

neural networks. Since the majority of neural networks are simulated on sequential
machines, giving rise to a very rapid increase in processing time requirements as size of
the problem expands.
Solution: implement neural networks directly in hardware, but these need a lot of
development still.
2. Instability to explain any results that they obtain. Networks function as "black boxes"
whose rules of operation are completely unknown.

27
5.9 Future Of Neural Networks:
Because gazing into the future is somewhat like gazing into a crystal ball, so it is better to quote
some "predictions". Each prediction rests on some sort of evidence or established trend which,
with extrapolation, clearly takes us into a new realm.

Prediction1:
Neural Networks will fascinate user-specific systems for education, information processing, and
entertainment. "Alternative ralities", produced by comprehensive environments, are attractive in
terms of their potential for systems control, education, and entertainment. This is not just a far-
out research trend, but is something which is becoming an increasing part of our daily existence,
as witnessed by the growing interest in comprehensive "entertainment centers" in each home.
This "programming" would require feedback from the user in order to be effective but simple
and "passive" sensors (e.g fingertip sensors, gloves, or wristbands to sense pulse, blood pressure,
skin ionisation, and so on), could provide effective feedback into a neural control system. This
could be achieved, for example, with sensors that would detect pulse, blood pressure, skin
ionisation, and other variables which the system could learn to correlate with a person's response
state.

Prediction2:
Neural networks, integrated with other artificial intelligence technologies, methods for direct
culture of nervous tissue, and other exotic technologies such as genetic engineering, will allow us
to develop radical and exotic life-forms whether man, machine, or hybrid.

Prediction3:
Neural networks will allow us to explore new realms of human capabillity realms previously
available only with extensive training and personal discipline. So a specific state of consiously
induced neurophysiologically observable awareness is necessary in order to facilitate a man
machine system interface.

28
5.10 Gallery:

A single-layer feed forward artificial neural network. Arrows originating from are omitted for
clarity. There are p inputs to this network and q outputs. In this system, the value of the qth

output would be calculated as .

A two-layer feedforward artificial neural network.

A two-layer feed forward artificial neural network with 8 inputs, 2x8 hidden and 2 outputs.
Given position state, direction and other environment values outputs thruster based control
values.

29
 6.ACHIEVEMENTS OF ARTIFICIAL INTELLIGENCE

a. DARPA Grand challenge- 123 miles through the desert

i.

b. DARPA Urban Challenge- Autonomous driving in traffic

c. Deep Thought is an international grand master chess player.

d. Sphinx can recognize continuous speech without training for each speaker. It
operates in near real time using a vocabulary of 1000 words and has 94% word
accuracy.
e. Navlab is a truck that can drive along a road at 55mph in normal traffic.
f. Carlton and United Breweries use an AI planning system to plan production of
their beer.
g. Natural language interfaces to databases can be obtained on a PC.
h. Machine Learning methods have been used to build expert systems.
i. Expert systems are used regularly in finance, medicine, manufacturing, and
agriculture
7.LONG TERM GOALS OF ARTIFICIAL
INTELLIGENCE

30
Among the long-term goals in the research pertaining to artificial intelligence are:

(1) Social intelligence

(2) Creativity

(3) General intelligence.

Social Intelligence:

Kismet, a robot with rudimentary social skills

Affective computing is the study and development of systems and devices that can recognize,
interpret, process, and simulate human affects It is an interdisciplinary field spanning computer
sciences, psychology, and cognitive science. While the origins of the field may be traced as far
back as to early philosophical inquiries into emotion,[86] the more modern branch of computer
science originated with Rosalind Picard's 1995 paper on affective computing. A motivation for
the research is the ability to simulate empathy. The machine should interpret the emotional state
of humans and adapt its behaviour to them, giving an appropriate response for those emotions.

Emotion and social skills play two roles for an intelligent agent. First, it must be able to predict
the actions of others, by understanding their motives and emotional states. (This involves
elements of game theory, decision theory, as well as the ability to model human emotions and the
perceptual skills to detect emotions.) Also, in an effort to facilitate human-computer interaction,
an intelligent machine might want to be able to display emotionseven if it does not actually

31
experience them itselfin order to appear sensitive to the emotional dynamics of human
interaction.

Creativity:

A sub-field of AI addresses creativity both theoretically (from a philosophical and psychological

perspective) and practically (via specific implementations of systems that generate outputs that
can be considered creative, or systems that identify and assess creativity). Related areas of
computational research are Artificial intuition and Artificial thinking.

General Intelligence:

Many researchers think that their work will eventually be incorporated into a machine
with general intelligence (known as strong AI), combining all the skills above and exceeding
human abilities at most or all of them. A few believe that anthropomorphic features like artificial
consciousness or an artificial brain may be required for such a project.

Many of the problems above may require general intelligence to be considered solved. For
example, even a straightforward, specific task like machine translation requires that the machine
read and write in both languages (NLP), follow the author's argument (reason), know what is
being talked about (knowledge), and faithfully reproduce the author's intention (social
intelligence). A problem like machine translation is considered "AI-complete". In order to solve
this particular problem, one must solve all the problems.

8. FUTURE OF ARTIFICIAL INTELLIGENCE

32
Having discussed about AI one debatable question arises that is artificial intelligence more
powerful than natural intelligence. Looking at the features and its wide applications we may
definitely stick to artificial intelligence. Seeing at the development of AI, is it that the future
world is becoming artificial.

Biological intelligence is fixed, because it is an old, mature paradigm, but the new paradigm of
non-biological computation and intelligence is growing exponentially. The crossover will be in
the 2020s and after that, at least from a hardware perspective, non-biological computation will
dominate.

The memory capacity of the human brain is probably of the order of ten thousand million binary
digits. But most of this is probably used in remembering visual impressions, and other
comparatively wasteful ways. One might reasonably hope to be able to make some real progress
[towards artificial intelligence] with a few million digits [of computer memory].

Hence we can say that as natural intelligence is limited and volatile too world may now depend
upon computers for smooth working.

9. CONCLUSION

33
Till now we have discussed in brief about Artificial Intelligence. We have discussed some of its
principles, its applications, its achievements etc. The ultimate goal of institutions and scientists
working on AI is to solve majority of the problems or to achieve the tasks which we humans
directly cant accomplish. It is for sure that development in this field of computer science will
change the complete scenario of the world. Now it is the responsibility of creamy layer of
engineers to develop this field.

We conclude that if the machine could successfully pretend to be human to a knowledgeable

observer then you certainly should consider it intelligent. AI systems are now in routine use in
various field such as economics, medicine, engineering and the military, as well as being built
into many common home computer software applications, traditional strategy games etc.

AI is an exciting and rewarding discipline. AI is branch of computer science that is

concerned with the automation of intelligent behavior. The revised definition of AI is -
AI is the study of mechanisms underlying intelligent behavior through the construction
and evaluation of artifacts that attempt to enact those mechanisms. So it is concluded that it
work as an artificial human brain which have an unbelievable artificial thinking power.

34
 Programs with Common Sense :-
John McCarthy, In Mechanization of Thought Processes, Proceedings of the Symposium
of the National Physics Laboratory, 1959.

Artificial Intelligence, Logic and Formalizing Common Sense :-

Richmond Thomason, editor, Philosophical Logic and Artificial Intelligence. Klver
Academic, 1989.

Concepts of Logical AI :-
Tom Mitchell.
Machine Learning.
McGraw-Hill, 1997.

Logic and artificial intelligence :-

Richmond Thomason.
In Edward N. Zalta, editor, The Stanford Encyclopedia of Philosophy. Fall 2003.
http://plato.stanford.edu/archives/fall2003/entries/logic-ai/.

LINKS :-

http://www.aaai.org/

http://www-formal.stanford.edu/

http://insight.zdnet.co.uk/hardware/emergingtech/

http://www.genetic-programming.com/

https://en.wikipedia.org/wiki/Artificial_intelligence

35