• No results found

Fig 1. Neural Network in human body

N/A
N/A
Protected

Academic year: 2022

Share "Fig 1. Neural Network in human body"

Copied!
6
0
0

Loading.... (view fulltext now)

Full text

(1)

Rohan Khanna, IJRIT 271

International Journal of Research in Information Technology (IJRIT)

www.ijrit.com ISSN 2001-5569

Study of Artificial Neural Network

Rohan Khanna1

,

Piyush2, Puneet Bhalla3

Student , Computer Science Engineering, MDU University, Delhi, India rohankhanna1993@gmail.com

Student , Computer Science Engineering, MDU University, Gurgaon , Haryana , India piyushchutani261993@gmail.com

Student , Computer Science Engineering, MDU University, Gurgaon , Haryana , India puneetbhalla24@gmail.com

Abstract

In this paper, we are focusing on Artificial Neural Network its characteristics and its numerous applications. It will help people which either does not know about it or have a little knowledge related to it. This paper will show “what are neural network” and how they work. Many researchers from many scientific disciplines are designing Artificial Neural Networks (ANNs) to solve numerous problems as it provides an exciting alternative.

Keywords: Artificial Neural Network, ANN, Artificial Neuron, Characteristics, Applications

1. Introduction

The subject of biology was the core foundation of the concept of ANNs. These are massively interconnected parallel computing systems consisting of an extremely large numbers of simple processors. Human body can be regarded as an example of parallel processing

Fig 1. Neural Network in human body

(2)

Rohan Khanna, IJRIT 272 A neuron is a special biological cell that process information from one neuron to another neuron. It is composed of soma or cell body and two types of out reaching branches: the axon and the dendrites. The cell body has a nucleus that contains information about hereditary traits and the plasma that holds the molecular equipments or producing the material needed by the neurons. A neuron receives the signals from other neurons through dendrites and transmits signals generated by its cell body along the axon which eventually branches into strands and substrands.

Fig. 2 Human Neurons

2. Artificial Neural Network

An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems such as brain process information

.

2.1 Artificial Neurons

An artificial neuron is a computational model inspired in the natural neurons. Natural neurons receive signals through synapses located on the dendrites or membrane of the neuron. When the signals received are strong enough, the neuron is activated and emits a signal through axon.

Fig.3 Artificial Neuron

3. Differences between the Modern computers and the Biological systems.

1) While the modern computers have few or local processors which are high speed but comples whereas Biological systems contains large number of processors which have low speed and are simple in nature.

2) The computers have localized memory separate from processor whereas Neural system has Distributed memory but integrated in the processor.

(3)

Rohan Khanna, IJRIT 273 3) In computers computing is done in sequential and centralized manner whereas in biological system computing

is done by self learning in a parallel and distributed manner.

4) In terms of reliability computers are very vulnerable whereas neural systems are robust.

5) The Operating environment is well defined and well constrained in the computers whereas the operating environment is poorly defined and unconstrained.

4. Working of ANN

The art of using neural networks revolve around the countless number of ways these individual neurons can be clustered together. This clustering occurs in the human mind in such a way that information can be processed in a dynamic, interactive, and self-organizing way. Biologically, neural networks are constructed in a three-dimensional world from microscopic components. These neurons seem capable of nearly unrestricted interconnections. That is not true of any proposed, or existing, man-made network. Integrated circuits, using current technology, are two- dimensional devices with a limited number of layers for interconnection. Currently, neural networks are the simple clustering of the primitive artificial neurons and it occurs by creating layers which are then connected to one another.

Fig. 4 A Simple Neural Network

Basically, all artificial neural networks have a similar structure. In that structure some of the neurons interfaces to the real world to receive its inputs. Other neurons provide the real world with the network's outputs. This output might be the particular character that the network thinks that it has scanned or the particular image it thinks is being viewed.

Fig. 5 Multilayered artificial neural network

(4)

Rohan Khanna, IJRIT 274 Most applications require networks that contain at least the three normal types of layers - input, hidden, and output.

The layer of input neurons receive the data either from input files or directly from electronic sensors in real-time applications. The output layer sends information directly to the outside world, to a secondary computer process, or to other devices such as a mechanical control system. The hidden layer receives the signals from all of the neurons in a layer above it, typically an input layer. After a neuron performs its function it passes its output to all of the neurons in the layer below it, providing a path to the output. Between these two layers can be many hidden layers.

The inputs and outputs of each of these hidden neurons go to other neurons.

5. ANN Characteristics

Primarily Computers are good in calculations that takes inputs process then and after that gives the result on the basis of calculations using particular Algorithm which are programmed in the software’s but ANN improve their own protocols, the more decisions they make, the better decisions may become.

The core six characteristics of ANN are:-

1) Network Structure

The Network Structure of ANN should be simple and easy. There are basically two types of structures recurrent and non recurrent structure. The Recurrent Structure is also known as Auto associative or Feedback Network and the Non Recurrent Structure is also known as Associative or Feed forward Network In Feed forward Network, the signal travel in one way only but in Feedback Network, the signal travel in both the directions by introducing loops in the network

2) Parallel Processing Ability

ANN is only introduce to enlarge the concept of parallel processing in the computer field. Parallel Processing is done by the human body in human neurons are very complex but by applying basic and simple parallel processing techniques we implement it in ANN like Matrix and some matrix calculations.

3) Distributed Memory

ANN is very huge system so single place memory or centralized memory cannot fulfill the need of ANN system so in this condition we need to store information in weight matrix which is form of long term memory because information is stored as patterns throughout the network structure

4) Fault Tolerance Ability

ANN is a very complex system so it is necessary that it should be a fault tolerant. Because if any part becomes fail it will not affect the system as much but if the all parts fails at the same time the system will fails completely

5) Collective Solution

ANN is an interconnected system where the output of a system is a collective output of various input so the result is summation of all the outputs which comes after processing various inputs. The Partial answer is worthless for any user in the ANN System.

(5)

Rohan Khanna, IJRIT 275

6) Learning Ability

In ANN most of the learning rules are used to develop models of processes, while adopting the network to the changing environment and discovering useful knowledge. These Learning methods are Supervised, Unsupervised and Reinforcement Learning.

Fig. Network Architecture

6. Applications

There are various real time applications of artificial neural network are:-

1) Function approximation, or regression analysis, including time series prediction and modelling 2) Call control- answer an incoming call (speaker-ON) with a wave of the hand while driving.

3) Scroll Web Pages, or within an eBook with simple left and right hand gestures, this is ideal when touching the device is a barrier such as wet hands are wet, with gloves, dirty etc.

4) system identification and control (vehicle control, process control)

5) pattern recognition (radar systems, face identification, object recognition, etc.)

6) Data processing, including filtering, clustering, blind signal separation and compression

7) Skip tracks or control volume on your media player using simple hand motions- lean back, and with no need to shift to the device- control what you watch/ listen to.

(6)

Rohan Khanna, IJRIT 276

7. CONCLUSIONS

By studying about the artificial neural network we concluded that it is a technology which is on continuous improvement as per every passing second. In this paper we discussed about artificial neural network, artificial neurons. We also mentioned the difference between the modern computers and biological neural systems. There are various characteristics related to ANNs which are very important and each of which is explained.

Since this technology is vastly improving as per every day thus there are numerous applications are also related to it which can also be termed as real time applications.

References

[1] Herve Debar, Monique Becker and Didier Siboni “A Neural Network Component for an Intrusion Detection System”, Les Ulis Cedex France, 1992,

[2] Ajith Abraham, “Artificial Neural Networks”, Stillwater,OK, USA, 2005.

[3] Carlos Gershenson, “Artificial Neural Networks for Beginners”, United kingdom.

[4] Anil K Jain, Jianchang Mao and K.M Mohiuddin, “Artificial Neural Networks: A Tutorial”, Michigan State university, 1996.

[5] Ugur HALICI, “ Artificial Neural Networks”, Chapter 1, ANKARA

[6] Eldon Y. Li, “ Artificial Neural Networks and their Business Applications”, Taiwan, 1994. [7] Christos Stergiou and Dimitrios Siganos, “Neural Networks”.

[8] Limitations and Disadvantages of Artificial Neural Network from website http://www.ncbi.nlm.nih.gov/pubmed/8892489

[9]Image of a Neuron form website http://transductions.net/ 2010/02/04/313/neurons/ [10]About Artificial Neural Network from website http:// en.wikipedia.org/wiki/Artificial_neural_network

[11] RC Chakraborty, “Fundamentals of Neural Networks”, myreaders.info/html/artificial_intelligence.html, june 01, 2010.

[12] Prof. Leslie Smith, “ An Introduction to Neural Networks”, University of Stirling., 1996,98,2001,2003.

[13] Prof. Dr. Eduardo Gasca A., “ Artificial Neural Networks”, Toluca

[14] Kishan Mehrotra, Chilukuri K Mohan and Sanjay Ranka “Elements of artificial neural network”, 1996 [15]Weyiu Yi 339229, “ Artificial Neural Networks”, 2005.

[16]Vincent Cheung and Kevin Cannons, “ An Introduction of Neural Networks”, Manitoba, Canada, May 27, 2002.

[17]Howard Demuth and Mark Beale, “ Neural Network Toolbox”, With the help of metlab, user guide version 4.

[18]Girish Kumar Jha, “Artificial Neural Network and its Applications”,IARI New delhi.

[19] About Neural Network from website http://en.wikipedia.org / wiki/Neural_network . [20] About Feed Back Network from website http://www.idsia.ch/ ~juergen/rnn.html . [21] Sucharita Gopal, “Artificial Neural Networks for Spatial Data Analysis”, Boston, 1988

[22]Bradshaw, J.A., Carden, K.J., Riordan, D., 1991. Ecological ―Applications Using a Novel Expert System Shellǁ. Comp. Appl. Biosci. 7, 79–83.

[23] Lippmann, R.P., 1987. An introduction to computing with neural nets. IEEE Accost. Speech Signal Process.

Mag., April: 4-22.

[24] N. Murata, S. Yoshizawa, and S. Amari, ―Learning curves, model selection and complexity of neural networks,ǁ in Advances in Neural Information Processing Systems 5, S. Jose Hanson, J. D. Cowan, and C. Lee Giles, ed. San Mateo, CA: Morgan Kaufmann, 1993, pp. 607-614

[25] A Comprehensive Study of Artificial Neural Networks, International Journal of Advanced Research in Computer Science and Software Engineering, Volume 2, Issue 10, October 2012, ISSN: 2277 128X [26] Artificial Neural Networks for Beginners, Carlos Gershenson, C.Gershenson@sussex.ac.uk

[27] Research Paper on Basic of Artificial Neural Network by Ms. Sonali. B. Maind Department of Information Technology Datta Meghe Institute of Engineering, Technology & Research, Sawangi (M), Wardha and Ms.

Priyanka Wankar Department of Computer Science and Engineering Datta Meghe Institute of Engineering, Technology & Research, Sawangi (M) International Journal on Recent and Innovation Trends in Computing and Communication ISSN: 2321-8169 Volume: 2 Issue: 1 96 – 100

References

Related documents

The organizers of the joint meeting of the Slovak Economic Association (SEA) and the Austrian Economic Association (NOeG) are soliciting papers for the 2016 conference, to be held

Understanding that native Arabic speakers transfer their L1 reading strategy to English, and that this results in less sensitivity to phonological information during reading,

You need to create an immediate good impression and the best way to do this in my experience is to present a well-structured piece of writing with clearly laid out paragraphs..

The present research aims to investigate the relationship between belief in a just world (BJW) and the symptoms of psychological disorders given the intermediate

The Board hereby determines that the Port Authority, in order to carry out its functions as an Ohio port authority, and pursuant to the authorization in Section

This may suggest that the Zimbabwe mate choice phenotype is a response to this putatitive DMI, providing strong selective pressure for the fixation of the Zimbabwe alleles of rim

Interestingly, similar mean sediment size (which can be known as coarse sand) was found along the river stretch up to the point SL 6. The type of land use here is dominated

(i) A candidate who having pursued a regular course of study in First and Second Semesters fails to appear at the main examination of First and Second Semesters, held for