Study on Elman Neural Networks Algorithms Based on Factor Analysis

Abstract:

When we manipulate high dimensional data with Elman neural network, many characteristic variables provide enough information, but too many network inputs go against designing of the hidden-layer of the network and take up plenty of storage space as well as computing time, and in the process interfere the convergence of the training network, even influence the accuracy of recognition finally. Factor Analysis (FA) concentrates the information that is carried by numerous original indexes which form the index system, and then stores it to the factor, and can according to the precision that the actual problem needs, through controlling the number of the factors, to adjust the amount of the information. In this paper we make full use of the advantages of FA and the properties of Elman neural network structures to establish FA-Elman algorithm. The new algorithm reduces dimensions by FA, and carry on network training and simulation with low dimensional data that we get, which obviously simplifies the network structure, and in the process, improves the training speed and generalization capacity of the Elman neural network.

• Periodical: Applied Mechanics and Materials (Volumes 511-512)
• Pages: 945-949
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.511-512.945
• Online since: February 2014
• Authors: Shao Xue Jing, Wei Kuan Jia
• Keywords: Elman Neural Network (ENN), Factor Analysis (FA), Fa-Elman Algorithm

References

[1] S Mccllochw, W Pitts. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 1943, 10(5): 115-133.

DOI: 10.1007/bf02478259

[2] J L Elman. Finding structure in time. Cognitive Science, 1990, 14(2): 179-211.

[3] S.F. Ding, W.K. Jia, C.Y. Su, et al. A Survey on Statistical Pattern Feature Extraction]. Lecture Notes in Artificial Intelligence, 2008, 5227: 701–708.

[4] S.F. Ding, H. Zhu, W.K. Jia, et al. A survey on feature extraction for pattern recognition. Artificial Intelligence Review, 2012, 37(3): 169-180.

DOI: 10.1007/s10462-011-9225-y

[5] S.F. Ding, W.K. Jia, F.X. Jin, et al. The Research of Neural Network Algorithm Based on Factor Analysis and Cluster Analysis. Neural Computing and Applications. 2011, 20(2): 297-302.

DOI: 10.1007/s00521-010-0416-2

[6] S.F. Ding, W.K. Jia, X.Z. Xu, et al. Neural Networks Algorithm Based on Factor Analysis. Lecture Notes in Computer Science, 2010, 6063: 319-324.

DOI: 10.1007/978-3-642-13278-0_41

[7] E.S. Gopi. Digital image forgery detection using artificial neural network and independent component analysis. Applied Mathematics and Computation, 2007, 194(2): 540-543.

DOI: 10.1016/j.amc.2007.04.055

[8] C Melchiorre, M Matteucci, A Azzoni, et al. Artificial neural networks and cluster analysis in landslide susceptibility zonation. Geomorphology, 2008, 94(3): 379-400.

DOI: 10.1016/j.geomorph.2006.10.035

[9] W G Yan, G X Liu, J Yang. Quality modeling of mechanical product based on PCA and Elman neural network. Science Technology and Engineering, 2007, 7(19): 5091-5095.

[10] D E Rumelhart, G E Hinton, R J Williams. Learning representation by Back-Propagating errors. Nature, 1986, 3(6): 533-536.

DOI: 10.1038/323533a0

[11] S.F. Ding, W.K. Jia, C.Y. Su. PCA-based Elman Neural Network Algorithm. Lecture Notes in Computer Science, 2008, 5370: 315-321.

DOI: 10.1007/978-3-540-92137-0_35

[12] http: /www. ics. uci. edu/~mlearn/databases/ionosphere/ [OL].