Abstract
This paper introduces how to use multi-valued PCNN (Pulse Coupled Neural Network) proposed in this paper to do classification. 2-dimensional data can be projected onto two-dimensional PCNN locally laterally linked. Different pulse waves generated by training data label different regions corresponding to different classes. The same pulse wave labels the region corresponding to the same class. Meeting of different pulse waves obtains the separatrixes of different classes. In order to differentiate different pulse waves, outputs of neurons in PCNN should be multi-valued. We call networks composed of these neurons multi-valued PCNNs. The number of classes determines the number of output value of each neuron. N-valued PCNN can be used to classify N-1 different classes. Experimental results of the 2-dimensional salmon-weever classification show that the correct recognition rate of test set is 98.11% (3477/3544) when training samples are only 10% of all samples.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Eckhorn, R., Reitboeck, H.J., Arndt, M., et al.: Feature Linking via Synchronization among Distributed Assemblies: Simulation of Results from Cat Cortex. Neural Computation 2, 293–307 (1990)
Eckhorn, R., Bauer, R., Jordan, W., et al.: Coherent oscillations: a mechanism of feature linking in the visual cortex? Multiple electrode and correlation analyses in the cat. Biological Cybernetics 60, 121–130 (1988)
Gray, C.M., Konig, P., Engel, A.K., Singer, W.: Oscillatory responses in cat visual cortex exhibitioner-columnar synchronization which reflects global stimulus properties. Nature 338, 334–337 (1989)
Eckhorn, R., Frien, A., Bauer, R., et al.: High frequency oscillations in primary visual cortex of awake monkey. NeuroRep. 4, 243–246 (1993)
Johnson, J.L., Ritter, D.: Observation of Periodic Waves in a Pulse-coupled Neural Network. Opt. Lett. 18, 1253–1255 (1993)
Johnson, J.L., Padgett, M.L.: PCNN Models and Applications. IEEE Trans. on Neural Networks 10, 480–498 (1999)
Kuntimad, G., Ranganath, H.S.: Perfect Image Segmentation Using Pulse Coupled Neural Networks. IEEE Trans. on Neural Networks 10, 591–598 (1999)
Broussard, R.P., Rogers, S.K., Oxley, M.E., Tarr, G.L.: Physiologically Motivated Image Fusion for Object Detection using a Pulse Coupled Neural Network. IEEE Trans. on Neural Networks 10, 554–563 (1999)
Kinser, J.M.: Foveation by a Pulse-Coupled Neural Network. IEEE Trans. on Neural Networks 10, 621–625 (1999)
Gu, X.D., Yu, D.H., Zhang, L.M.: Image Thinning Using Pulse Coupled Neural Network. Pattern Recognition Letters 25, 1075–1084 (2004)
Gu, X.D., Yu, D.H., Zhang, L.M.: Image Shadow Removal Using Pulse Coupled Neural Network. IEEE Trans. on Neural Networks 16, 692–698 (2005)
Caulfield, H.J., Kinser, J.M.: Finding Shortest Path in the Shortest Time Using PCNN’s. IEEE Trans. on Neural Networks 10, 604–606 (1999)
Gu, X.D., Guo, S.D., Yu, D.H.: A New Approach for Automated Image Segmentation Based on Unit-linking PCNN. In: Proceedings in IEEE International Conference on Machine learning and Cybernetics, Beijing, China, pp. 175–178 (2002)
Gu, X.D.: A New Approach to Image Authentication Using Local Image Icon of Unit-linking PCNN. In: Proceedings in Int. Joint Conf. Neural Networks, Vancouver, Canada, pp. 2015–2020 (2006)
Gu, X.D., Zhang, L.M., Yu, D.H.: General Design Approach to Unit-linking PCNN for Image Processing. In: Proceedings in Int. Joint Conf. Neural Networks, Montreal, Canada, pp. 1836–1841 (2005)
Gu, X.D., Zhang, L.M.: Global Icons and Local Icons of Images based Unit-linking PCNN and their Application to Robot Navigation. In: Wang, J., Liao, X.-F., Yi, Z. (eds.) ISNN 2005. LNCS, vol. 3497, pp. 836–841. Springer, Heidelberg (2005)
Gu, X.D.: Research on Pulse Coupled Neural Network and its Applications. Ph.D. dissertation, Peking University (2003)
Gu, X.D.: Research on several Theoretical and Applied Aspects on Unit-linking Pulse Coupled Neural Network. Post-doctoral research report, Fudan University (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gu, X. (2008). Classification Using Multi-valued Pulse Coupled Neural Network. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4985. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69162-4_57
Download citation
DOI: https://doi.org/10.1007/978-3-540-69162-4_57
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69159-4
Online ISBN: 978-3-540-69162-4
eBook Packages: Computer ScienceComputer Science (R0)