Abstract
A new Fuzzy ART neural network model based on dual competition and resonance technique is proposed. This new model takes the competition and resonance method of the input nodes into the output nodes, putting the input nodes and output nodes competition and resonance together, solves the over-segmentation of the FART algorithm due to the vigilance’s increase in the application of the image segmentation. Experimental results have shown that compared with the original FART, this algorithm has a better segmentation and antinoise performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Carpenter, G.A., Grossberg, S., Rosen, D.B.: Fuzzy ART: Fast Stable Learning and Categorization of Analog Patterns by an Adaptive Resonance System. Neural Networks 4, 759–771 (1991)
Carpenter, G.A., Grossberg, S.: Markuzon: Fuzzy ARTMAP: An Earning of Analog Multidimensional Supervised Maps. IEEE Transactions on Neural Networks 3, 698–613 (1992)
Huang, J., Georgiopoulos, M., Heileman, G.L.: Fuzzy ART Properties. Neural Networks 8, 202–213 (1995)
Williamson, J.R.: Gaussian ARTMAP: A Neural Network for Fast Incremental Learning of Noisy Multidimensional Maps. Neural Networks 9, 881–897 (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, L., Wang, G., Wang, W. (2006). A New Fuzzy ART Neural Network Based on Dual Competition and Resonance Technique. In: Wang, J., Yi, Z., Zurada, J.M., Lu, BL., Yin, H. (eds) Advances in Neural Networks - ISNN 2006. ISNN 2006. Lecture Notes in Computer Science, vol 3971. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11759966_116
Download citation
DOI: https://doi.org/10.1007/11759966_116
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34439-1
Online ISBN: 978-3-540-34440-7
eBook Packages: Computer ScienceComputer Science (R0)