Open Access Open Access  Restricted Access Subscription or Fee Access

Analytical Study on Artificial Neural Network Learning Algorithms and Technique

P. Nalini, M. Jeevitha

Abstract


The artificial neural networks are widely used to support the human decision capabilities, avoiding inconsistency in practice and errors based on lack of experience. In this paper various learning rules in artificial neural networks like preceptron learning, error correction, hebbian and competition learning rules are explored. Learning rules are algorithms which direct changes in the weights of the connections in a network. They are incorporating an error reduction procedure by employing the difference between the desired output and an actual output to change its weights during training. The learning rule is typically applied repeatedly to the same set of training inputs across a large number of epochs with error gradually reduced across epochs as the weights are fine-tuned.  This paper also focuses on one of the neural network technique called Multilayer perceptron (MLP) along with its applications and advantages and drawbacks

Keywords


Artificial Neural Networks, Perceptron Learning, Error Correction, Memory Based, Hebbian, and Competition Learning, MLP.

Full Text:

PDF

References


Harun, N.; Woo, W.L. ; Dlay, S.S. ;” Performance of keystroke biometrics Authentication system using Artificial Neural Network (ANN) and Distance Classifier Method " International Conference on Computer and Communication Engineering (ICCCE), 2010

S. Modi and S. J. Elliott, “Keystroke dynamics verification using a spontaneously generated password password,” in Proc. 40th Annu. Int. Carnahan Conf.Security Technol., Lexington, KY, Oct. 2006, pp. 116–121.

A. Peacock, X. Ke, and M. Wilkerson, “Typing patterns: A key to user identification,” IEEE Security Privacy, vol. 2, no. 5, pp. 40– 47, Sep./Oct. 2004.

N. Capuano, M.Marsella, S.Miranda and S. Salerno, “User Authentication with Neural networks”, Univerity of Salerno Italy. http://www.capuano.biz/Papers/EANN_99.pdf

R. O. Duda, P. E. Hart, and D. G. Stork. Pattern Classification,2ndedition, John Wiley & Sons, Inc.,2001

S R Shorrock, D J Atkinson, S S Dlay, Biometric verification of computer users with probabilistic and cascade forward neural networks.

Ross, A., Shah, J., & Jain, A. K. March 2005. Towards reconstructing fingerprints from minutiae points. Proceedings of SPIE Conference on Biometric Technology for Human IdentificationII, 5779, 68–80.

M.S. Obaidat and D.T Macchairolo, “A multilayer neural network for computer access security”, IEEE transactions on Systems, Machine and Cybernetics, vol 24(5), (1994).

S.Bleha and M. obaidat. Computer users verification using the perceptron algorithm. IEEE Transactions on Systems, Man and Cybernetics, 23(3):900 -902, May. 1993

Kohonen T.Analysis of A Simple Self-Organizing Process [M].Biol.cybern, 1982(44):135-140.

Flanagan J A.Self-organisation in Kohonen's SOM [J].NeuralNetworks, 1996, 9(7):1185-1197.

W. Yan, “Toward automatic time-series forecasting using neural networks”, IEEE transaction on neural networks and Learning Systems, 2012, 7(23):1028-1039.

R. R. Andrawis and A. F. Atiya, “A new Bayesian formulation for holt’s exponential smoothing,” Journal of Foresting, 2009, 3(28):218-234.

I. Maqsood, M. Khan, and A. Abraham, “An ensemble of neural networks for weather forecasting”, Neural computing and applications, 2004, 2(13):1012-122.

D. F. Specht, “Probabilistic neural networks”, Neural Networks”, 1990(3):109-118.

W. T. Miller III, F. H. Glanz and G.Kraft III, “CMAC: an associative neural network alternative to backprogation,”Proc.

Shantakumar B. Patil, S. Kumarswamy, Intelligent an and Effective Heart Attack Prediction System Using Data Mining and Artificial Neural Network, European Journal of Scientific Research,2009,4(31):1450-216X

S. Haykin, Neural Networks A Comprehensive Foundation Prentice Hall, 2000(2).

G. E. Hinton, S. Osindero, and Y. Teh. A fast learning algorithm for deep belief nets Neural Computation, 2006:1527-1554.




DOI: http://dx.doi.org/10.36039/AA052017003.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.