Effects of the number of hidden nodes used in a structuredbased neural network on the reliability of image classification
 Weibao Zou,
 Yan Li,
 Arthur Tang
 … show all 3 hide
Rent the article at a discount
Rent now* Final gross prices may vary according to local VAT.
Get AccessAbstract
A structuredbased neural network (NN) with backpropagation through structure (BPTS) algorithm is conducted for image classification in organizing a large image database, which is a challenging problem under investigation. Many factors can affect the results of image classification. One of the most important factors is the architecture of a NN, which consists of input layer, hidden layer and output layer. In this study, only the numbers of nodes in hidden layer (hidden nodes) of a NN are considered. Other factors are kept unchanged. Two groups of experiments including 2,940 images in each group are used for the analysis. The assessment of the effects for the first group is carried out with features described by image intensities, and, the second group uses features described by wavelet coefficients. Experimental results demonstrate that the effects of the numbers of hidden nodes on the reliability of classification are significant and nonlinear. When the number of hidden nodes is 17, the classification rate on training set is up to 95%, and arrives at 90% on the testing set. The results indicate that 17 is an appropriate choice for the number of hidden nodes for the image classification when a structuredbased NN with BPTS algorithm is applied.
Inside
Within this Article
 Introduction
 Description of feature sets for neural network
 Image sets for the experiment
 Effects of the numbers of hidden nodes on the reliability of image classification
 Discussion
 Conclusion
 References
 References
Other actions
 Zou W, Li Y, Lo KC, Chi Z (2006) Improvement of image classification with wavelet and independent component analysis (ICA) based on a structured neural network. Proceedings of IEEE world congress on computational intelligence’2006 (WCCI’2006), Vancouver, pp 7680–7685
 Zou W, Lo KC, Chi Z (2006) Structuredbased neural network classification of images using wavelet coefficients. In: Proceedings of third international symposium on neural networks (ISNN). Lecture notes in computer science 3972: advances in Neural NetworksISNN2006, part II Springer, Chengdu, pp 331–336
 Giles CL, Gori M (1998) Adaptive processing of sequences and data structures. Springer, Berlin
 Sperduti A, Starita A (1997) Supervised neural networks for classification of structures. IEEE Trans Neural Netw 8:714–735
 Goller C, Kuchler A (1996) Learning taskdependent distributed representations by backpropagation through structure. In: Proceedings IEEE international conference nerual networks, pp 347–352
 Cho SY, Chi ZR, Siu WC, Tsio AC (2003) An improved algorithm for learning longterm dependency problems in adaptive processing of data structures. IEEE Trans Neural Netw 14:781–793
 Wanas N, Auda G, Kamel MS, Karray F (1998) On the optimal number of hidden nodes in a neural network. IEEE Can Conf Elect Comp Eng 2:918–921
 Mirchandani G, Cao W (1989) On hidden nodes for neural nets. IEEE Trans Circuits Syst 36(5):661–664
 Nocera P, Quelavoine R (1994) Diminishing the number of nodes in multilayered neural networks. IEEE world congress on computational intelligence, pp 4421–4424
 Gorman RP, Sejnowski TJ (1988) Analysis of hidden units in a layered network trained to classify sonar targets. Neural Netw 1:75–89
 Rojas R (2003) Networks of width one are universal classifiers. In: Proceedings of the international joint conference on neural networks, pp 3124–3127
 How many hidden units should I use? http://www.faqs.org/faqs/aifaq/neuralnets/part3/section10.html (accessed 29 Aug 2007)
 Tsoi AC (1998) Adaptive processing of data structures: an expository overview and comments. Technical report. Faculty of Informatics, University of Wollongong, Australia
 Tsoi AC, Hangenbucnher M (1999) Adaptive processing of data structures. Keynote Speech. In: Proceedings of third international conference on computational intelligence and multimedia applications (ICCIMA ’99), 2–2 (summary)
 Frasconi P, Gori M, Sperduti A (1998) A general framework for adaptive processing of data structures. IEEE Trans Neural Netw 9:768–785
 Cho S, Chi Z, Wang Z, Siu W (2003) An efficient learning algorithm for adaptive processing of data structure. Neural Process Lett 17:175–190
 Dummer G, Winton R (1986) An elementary guide to reliability, 3rd edn. Pergamon Press, New York, 47p
 Snedecor GW, Cochran WG (1989) Statistical methods. Iowa State University press, Ames, 507p
 Title
 Effects of the number of hidden nodes used in a structuredbased neural network on the reliability of image classification
 Journal

Neural Computing and Applications
Volume 18, Issue 3 , pp 249260
 Cover Date
 20090401
 DOI
 10.1007/s0052100801773
 Print ISSN
 09410643
 Online ISSN
 14333058
 Publisher
 SpringerVerlag
 Additional Links
 Topics
 Keywords

 Hidden nodes
 Backpropagation through structure
 Image classification
 Neural network
 Features set
 Industry Sectors
 Authors

 Weibao Zou ^{(1)} ^{(2)}
 Yan Li ^{(3)}
 Arthur Tang ^{(4)}
 Author Affiliations

 1. Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong
 2. Shenzhen Institute of Advanced Technology, Shenzhen, China
 3. Department of Mathematics and Computing, The University of Southern Queensland, Toowoomba, QLD, Australia
 4. University of Central Florida, Orlando, FL, USA