Complex-Valued Multistate Associative Memory With Nonlinear Multilevel Functions for Gray-Level Image Reconstruction
Authors:
- 28 July 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 20 (9) , 1463-1473
Abstract
A widely used complex-valued activation function for complex-valued multistate Hopfield networks is revealed to be essentially based on a multilevel step function. By replacing the multilevel step function with other multilevel characteristics, we present two alternative complex-valued activation functions. One is based on a multilevel sigmoid function, while the other on a characteristic of a multistate bifurcating neuron. Numerical experiments show that both modifications to the complex-valued activation function bring about improvements in network performance for a multistate associative memory. The advantage of the proposed networks over the complex-valued Hopfield networks with the multilevel step function is more outstanding when a complex-valued neuron represents a larger number of multivalued states. Further, the performance of the proposed networks in reconstructing noisy 256 gray-level images is demonstrated in comparison with other recent associative memories to clarify their advantages and disadvantages.Keywords
This publication has 20 references indexed in Scilit:
- Improvements of Complex-Valued Hopfield Associative Memory by Using Generalized Projection RulesIEEE Transactions on Neural Networks, 2006
- Multistate associative memory with parametrically coupled map networks2005
- A new design method for the complex-valued multistate hopfield associative memoryIEEE Transactions on Neural Networks, 2003
- Neural associative memory storing gray-coded gray-scale imagesIEEE Transactions on Neural Networks, 2003
- PARAMETRICALLY COUPLED SINE MAP NETWORKSInternational Journal of Bifurcation and Chaos, 2001
- The Bifurcating Neuron Network 1Neural Networks, 2001
- Characteristics of the complex-valued associative memory model having penalty termElectronics and Communications in Japan (Part III: Fundamental Electronic Science), 2000
- Multi-Valued and Universal Binary Neurons2000
- Associative memory based on parametrically coupled chaotic elementsPhysica D: Nonlinear Phenomena, 1998
- Analysis and synthesis of a class of discrete-time neural networks with multilevel threshold neuronsIEEE Transactions on Neural Networks, 1995