Call for Paper - September 2022 Edition
IJCA solicits original research papers for the September 2022 Edition. Last date of manuscript submission is August 22, 2022. Read More

Reducing the Complexity of the Multilayer Perceptron Network using the Loading Matrix

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2020
Authors:
Mohamed Loay Dahhan, Yasser Almoussa
10.5120/ijca2020920568

Mohamed Loay Dahhan and Yasser Almoussa. Reducing the Complexity of the Multilayer Perceptron Network using the Loading Matrix. International Journal of Computer Applications 175(10):40-48, August 2020. BibTeX

@article{10.5120/ijca2020920568,
	author = {Mohamed Loay Dahhan and Yasser Almoussa},
	title = {Reducing the Complexity of the Multilayer Perceptron Network using the Loading Matrix},
	journal = {International Journal of Computer Applications},
	issue_date = {August 2020},
	volume = {175},
	number = {10},
	month = {Aug},
	year = {2020},
	issn = {0975-8887},
	pages = {40-48},
	numpages = {9},
	url = {http://www.ijcaonline.org/archives/volume175/number10/31492-2020920568},
	doi = {10.5120/ijca2020920568},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

In this paper, Researchers present three models of a Multilayer Perceptron Network (MLPs) based on the Factor Analysis with Principal Components method (PC) to reduce the degree of complexity of the neural network. In the first model, a neural network was built with all the variables in the input layer. In the second model, the results of the FA were adopted instead of the basic variables in the input layer, and in the third model, the Loading matrix was used to determine the number of nodes in the hidden layer and the weights that are associated with the input layer. Then compared the results of the models by determining the number of network weights that reflect the complexity of the network, in addition to the time of building and training the model and the accuracy of classification. The results of applying the models to a hypothetical database for the purposes of scientific research titled Bank Marketing showed that the model that inserted the factors in the hidden layer and preserved the high loading factors only is the best model in terms of low degree of complexity and maintaining classification accuracy.

References

  1. Mccllochw S, Pitts W, 1943, “A logical calculus of the ideas immanent in nervous activity”. Bull Math Biophys 10(5):115–133
  2. P. Jeatrakul, K.W. Wong, 2009. “Comparing the Performance of Different Neural Networks for Binary Classification Problems”. IEEE
  3. B. Widrow, D. Rumelhard, and M. A. Lehr, 1994. "Neural networks: Applications in industry, business and science," Communications of the ACM, vol.37, pp. 93-105.
  4. C. Charalambous, A. Charitou, and F. Kaourou, 2000, "Comparative analysis of artificial neural network models: application in bankruptcy prediction” in Neural Networks, IJCNN'99.International Joint Conference on Neural Networks, vol.6, pp. 3888-3893.
  5. L. Gang, B. Verma, and S. Kulkami, 2002. "Experimental analysis of neural network based feature extractors for cursive handwriting recognition," in Neural Networks. IJCNN '02. Proceedings of the 2002 International Joint Conference on Neural Networks, pp. 2837-2842.
  6. R. Rabuñal Juan, Dorado Julián, 2006. “Artificial Neural Networks in real life applications”, Idea group publishing, London.
  7. Cheng H, Cai X, Min R, 2009."A novel approach to color normalization using neural network”. Neural Computing and Applications 18(3), pp. 237–247.
  8. Rumelhart D, Hinton G, Williams R, 1986, “Learning representation by back-propagating errors”. Nature.com vol. 323, no. 6088, pp. 533–538,
  9. Gupta Tarun Kumar, Raza Khalid, 2018. "Optimizing Deep Neural Network Architecture: A Tabu Search Based Approach". Computer Science, springer.
  10. Agah Arvin, 2013. "Medical Applications of Artificial Intelligence", CRC Press, Tylor & Fracis Group. New York p. 204.
  11. M. Gross, H. Luttermann, "Combining principal component analysis and neural networks for the recognition of human faces- a case study for man - machine - communication, in: S.Y. Shin, T.L. Knuii (Eds.)",1993. Computer Graphics & Applications, Proceedings of the Pacific Graphics, vol. 1, pp. 176–192.
  12. T.M. Khoshgoftaar, R.M. Szabo, 1996. "Using neural networks to predict software faults during testing”, IEEE Transactions on Reliability, pp: 456–462.
  13. W.W. Hseih, B. Tang, 1998. "Applying neural network models to prediction and data analysis in meteorology and oceanography", Bulletin of the American Meteorological. Soc. 79 pp: 1855–1870.
  14. O’Farrella, et al., 2005. “Combining principal component analysis with an artificial neural network to perform online quality assessment of food as it cooks in a large-scale industrial oven”, Sensors and Actuators B, Vol. 107, pp. 104–112.
  15. Bucinski, A., Baczek, T., Wasniewski, T., and Stefanowicz, M., 2005. “Clinical data analysis with the use of artificial neural networks (ANN) and principal component analysis (PCA) of patients with endometrial carcinoma”, Reports on Practical Oncology and Radiotherapy, Vol. 10, pp. 239-248.
  16. Song J, Feng Y, 2006. "Hyperspectral data classification by independent component analysis and neural network". Remote sensing technology and application, pp. 115–119
  17. Zhang Y, 2007. "Artificial neural networks based on principal component analysis input selection for clinical pattern recognition analysis". Talanta 73(1) pp:68–75.
  18. Gopi E, 2007. "Digital image forgery detection using artificial neural network and independent component analysis". Appl Math Comput 194(2) pp:540–543.
  19. Sousa, S.I.V. , Martins, F.G. , Alvim-Ferraz, M.C.M., Pereira, M.C., 2007. “Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations”, Environmental Modelling & Software, Vol. 22, pp. 97-103.
  20. Ravi, V., Pramodh, C., 2008. “Threshold accepting trained principal component neural network and feature subset selection: Application to bankruptcy prediction in banks”, Applied Soft Computing, Vol. 8, pp. 1539–1548.
  21. Miguel Antonio, Llombart Jorge, Ortega Alfonso and Lleida Eduardo, 2017. “Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition”, In Proc. Interspeech, pp 2819–2823, Stockholm, Sweden.
  22. Ding Shifei et al. et al., 2010. "Research of neural network algorithm based on factor analysis and cluster analysis", Neural Comput & Applic (2011) 20:297–302 springer-Verlag London Limited.
  23. Zekić-Sušac Marijana et al., 2013. "Combining PCA analysis and artificial neural networks in modelling entrepreneurial intentions of students", Croatian Operational Research Review, Croatia, 4, P306-317.
  24. Taylor, Brian J., 2006. "Methods and Procedures for the Verification and Validation of Artificial Neural Networks", Springer Science & Business Media.
  25. P. Arumugam, R. Ezhilarasi, 2017. "Data Mining based Neural Network Model for Rainfall Forecasting", International Journal of Computer Applications, Volume 170 – No.4.
  26. Shafi Imran et al., 2006."Impact of Varying Neurons and Hidden Layers in Neural Network Architecture for a Time Frequency Application", IEEE International Multitopic Conference.
  27. Mehrotra K., Mohan C., Ranka S., 1997. "Element of Artificial Neural Networks", MIT Press, USA.
  28. S. Haykin, 2008. "Neural networks and learning machines", third edition, Prentice Hall.
  29. R. Rojas, 1996. "Neural networks - a systematic introduction”, Springer-Verlag.
  30. Dang Tuan Linh, Hoshino Yukinobu, 2019. "Improved PSO Algorithm for Training of Neural Network in Co-design Architecture", International Journal of Computer Applications, Volume 182 - No.44.
  31. Leskovec Jure, Rajaraman Anand, Ullman Jeffrey David, 2020. "Mining of Massive Datasets", Third edition, Cambridge University Press, pp. 517-520.
  32. Heaton Jeff, 2011. "Introduction to the Math of Neural Networks", Heaton Research, Inc., USA.
  33. Berrar Daniel, 2018. "Cross-validation", Encyclopedia of Bioinformatics and Computational Biology, Volume 1, Elsevier, pp. 542–545.
  34. Kamarthi, S. V., & Pittner, S. 1999. "Accelerating neural network training using weight extrapolations". Neural Networks, 12, 1285–1299.
  35. Du Ke-Lin, Swamy M. N. S., 2019. "Neural Networks and Statistical Learning", Springer-Verlag London, UK.
  36. Hagan Martin, Demuth Howard, Beale Mark, De Jesús Orlando, "Neural Network Design", Oklahoma State University, Stillwater, OK, United States, 2nd Edition, P13-1.
  37. Johnson Richard, Wichern Dean, 1998. "Applied Multivariate Statistical Analysis", fourth edition, prentice hall, Upper Saddle River, New jersey 07458.
  38. J,Salkind Neil, 2010. "Encyclopedia of Research Design", 1st Edition, Kindle Edition, SAGE Publications, pp. 460-466.
  39. Saurabh Karsoliya, 2012. “Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture” International Journal of Engineering Trends and Technology- Volume 3 Issue 6.
  40. S. Moro, P. Cortez and P. Rita. A Data-Driven Approach to Predict the Success of Bank Telemarketing. Decision Support Systems, In press, http://dx.doi.org/10.1016/j.dss.2014.03.01

Keywords

Multilayer Perceptron Network MLP, Factor Analysis FA, Principle Component Analysis PCA, Complexity, Loading Matrix