New supervised multi layer feed forward neural network model to accelerate classification with high accuracy

European Journal of Scientific Research

Volumn 33, Issue 1, 2009, Pages 163-178

  Asadi, Roya ^a   Mustapha, Norwati ^a   Sulaiman, Nasir ^a   Shiri, Nematollaah ^b  

^a UNIVERSITY PUTRA MALAYSIA   (Malaysia)

^b Dept of Electrical and Computer Engineering   (Canada)

Author keywords

Epoch; Pre training; Preprocessing; SMFFNN; SMNN; Training

Indexed keywords

EID: 68649125304     PISSN: 1450216X     EISSN: 1450202X     Source Type: Journal    
DOI: None     Document Type: Article

References (34)

1. Andonie, R. and Kovalerchuk, B. 2004. Neural Networks for Data Mining: Constrains and Open Problems. Computer Science Department Central Washington University, Ellensburg, USA.
2. Cios, K. J., Wedding, D. K. and Liu N., 1997. CLIP3: Cover learning using integer programming, Kybernetes 26 (4-5) (1997) 513-536.
3. Cios, K.J. and Liu, N. 1995. An Algorithm which Learns Multiple Covers via Integer Linear Programming. Part I--The CLILP2 Algorithm, Kybernetes, 24:2, pp. 29-50 (The Norbert Wiener Outstanding Paper Award).
4. Daffertshofer, A., Lamoth, C.J., Meijer, O.G. and Beek P.J. 2004. PCA in studying coordination and variability: a tutorial. Clin Biomech (Bristol, Avon).19:415-428.
5. Dasarathy, B.V. 1991. Nearest neighbor (NN) norms: NN pattern classification techniques. IEEE Comput. Soc. Press, Los Alamitos, CA.
6. DeMers, D. and Cottrell, G. 1993. Non-linear dimensionality reduction. In Advances in Neural Information Processing Systems, volume 5, pages 580-587, San Mateo, CA, USA. Morgan Kaufmann.
7. Demuth, H., Beale, M. and Hagan, M. 2007. Neural Network Toolbox User's GuideMatlab, The Mathworks, Accelerating the pace of engineering and science.
8. Drago, G.P. and Ridella, S. 1992. Statistically Controlled Activation Weight initialization (SCAWI). IEEE Transactions. on Neural Networks, vol. 3, no. 4, pp. 627-631.
9. Fernández-Redondo, M. and Hernández-Espinosa C. 2001. Weight Initialization Methods for Multilayer feed forward. Universidad Jaume I, Campus de Riu Sec, Edificio TI, Departamento de Informática, 12080 Castellón, Spain. ESANN'2001 proceedings - European Symposium on Artificial Neural Networks. Bruges (Belgium), 25-27 April 2001, D-Facto public., ISBN 2-930307-01-3, pp. 119-124.
10. Fernandez-Redondo, M. and Hernandez-Espinosa, C. 2000. A comparison among weight initialization methods for multilayer feedforward networks, Proceedings of the IEEE-INNS-177 ENNS International Joint Conference on Neural Networks, Vol. 4, Como, Italy, 2000, pp. 543-548.
11. Funahash, K. 1989. On approximate realization of continuous mappings by neural networks, Neural Networks 2. 183-192.
12. Han, J. and Kamber, M. 2001. Data Mining: Concepts and Techniques. Simon Fraser University, Academic Press.
13. Hegland, M. 2003. Data Mining - Challenges, Models, Methods and Algorithms. May 8. Scientific Literature Digital Library, citeseer.ist.psu.edu/context/68861/0.
14. Hinton, G.E. and Salakhutdinov, R.R. 2006. Reducing the Dimensionality of Data with Neural Networks. Materials and Methods. Figs. S1 to S5 Matlab Code. 10.1126/science. 1127647.June. www.sciencemag.org/cgi/content/full/313/5786/504/DC1
15. Ho-Sub, Y., Chang-Seok, B. and Byung-Woo, M. 1995. Neural networks using modified initial connection strengths by the importance of feature elements. In Proceedings of International Joint Conf. on Systems, Man and Cybernetics, 1: 458-461.
16. Jolliffe, L.T. 1986. Principal Component Analysis. Springer-Verlag, New York.
17. Jolliffe, L.T. 2002. Principal Component Analysis. Springer. 2nd edition.
18. Keeni, K., Nakayama, K. and Shimodaira, H. 1999. A training scheme for pattern classification using multi-layer feed-forward neural networks. In Proceedings of 3rd International Conference on Computational Intelligence and Multimedia Applications, New Delhi, India, pp. 307-311.
19. Kim, J.K. and Zhang, B.T. 2007. Evolving Hyper networks for Pattern Classification. In Proceedings of IEEE Congress on Evolutionary Computation. Page(s):1856 - 1862 Digital Object Identifier 10.1109/CEC.
20. Krzysztof J., Cios and Lukasz A.K. 2003. CLIP4: Hybrid inductive machine learning algorithm that generates inequality rules. Department of Computer Science and Engineering, University of Colorado at Denver, Campus Box 109, P.O. Box 173364, Denver, CO 80217-3364, USA. Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB T6G 2V4, Canada, Department of Computer Science, University of Colorado at Boulder, Boulder, CO 80309, USA. University of Colorado Health Sciences Center, Denver, CO 80262, USA. 4cData, Golden, CO 80401, USA. Received 8 May 2002; accepted 17 March 2003.
21. Lanckriet, G.R.G., Bartlett, P., Cristianini, N., Ghaoui, L. El and Jordan M. I. 2004. Learning the kernel matrix with semidefinite programming. Journal of Machine Learning Research, 5:27-72.
22. LeCun, Y., Bottou, L., Orr, G. and Muller, K. 1998. Efficient Back Prop. In Orr, G. B. and. Muller, K.-R., (Eds.), Neural Networks: Tricks of the trade, (G. Orr and Muller K., eds.).
23. Lindsay, S. 2002. A tutorial on Principal Components Analysis. February 26. Unpublished. T.Z.1-4244-1340-0/07/2007 IEEE URL://http://www.ics.uci.edu/mlearn/MLRepository.html
24. Mark W. Craven and Jude W. Shavlik, 1997. Using Neural Networks for Data Mining. Computer Science Department, Carnegie Mellon University, University of Wisconsin-Madison. Elsevier Science Publishers B. V. Amsterdam, The Netherlands, The Netherlands. ISSN: 0167-739X.
25. Mariyam, S. 2000. Higher Order Centralized Scale-Invariants for Unconstrained Isolated Handwritten Digits. PhD. Thesis, University Putra Malaysia.
26. P.M. Murphy, "Repository of Machine Learning and Domain Theories", 1997; http://archive.ics.uci.edu/ml/datasets/SPECTF+Heart; http://archive.ics.uci.edu/ml/datasets/SPECT+Heart.
27. Neal, M.J., Goodacre, R. and Kell, D.B. 1994. The analysis of pyrolysis mass spectra using artificial neural networks. Individual input scaling leads to rapid learning. In Proceedings of the World Congress on Neural Networks. International Neural Network Society San Diego, California, I-318 - I-323.
28. Russell, I.F. 2007. Neural Networks. Department of Computer Science. University of Hartford West Hartford, CT 06117. Journal of Undergraduate Mathematics and its Applications, Vol 14, No 1.
29. Shlens, J. 2005. A Tutorial on Principal Component Analysis. Unpublished, Version 2.
30. Van der Maaten, L.J.P., Postma, E., and van den Herik, H. 2008. Dimensionality Reduction: A Comparative Review. MICC, Maastricht University, P.O. Box 616, 6200 MD Maastricht, The Netherlands. Preprint submitted to Elsevier, 11 January.
31. Wang, J., Kwok, J.T., Shen, H.C. and Quan, L. 2005. Data-Dependent Kernels for High-Dimensional Data Classification. In Proceedings of International Joint Conference on Neural Networks, Montreal, Canada, July 31- August 4, 2005.0-7803-9048-2/05/2005 IEEE. Department of Computer Science The Hong Kong University of Science and Technology Clear Water Bay Hong Kong.
32. Werbos, P.J. 1974. PaulWerbos. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. PhD thesis, Committee on Applied Mathematics, Harvard University, Cambridge, MA, November 1974.
33. Zhang, X.M., Chen, Y.Q., Ansari, N. and Shi, Y.Q. 2003. Mini-max initialization for function Approximation. Department of Electrical & Computer Engineering, New Jersey Institute of Technology, Newark, NJ 07102, USA. Department of Computer Science and Engineering, Intelligent Information Processing Laboratory, Fudan University, People's Republic of China. Accepted 31 October 2003.
34. Yim, T.K. 2005. An Improvement on Extended Kalman Filter for Neural Network Training. Master Thesis, University Putra Malaysia.