A New Fuzzy ART Neural Network Based on Dual Competition and Resonance Technique
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.
KeywordsOutput Node Input Node Output Pattern Resonance Technique Activity Vector
Unable to display preview. Download preview PDF.
- 2.Carpenter, G.A., Grossberg, S.: Markuzon: Fuzzy ARTMAP: An Earning of Analog Multidimensional Supervised Maps. IEEE Transactions on Neural Networks 3, 698–613 (1992)Google Scholar