Document Detail


Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction.
MedLine Citation:
PMID:  19643705     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
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.
Authors:
Gouhei Tanaka; Kazuyuki Aihara
Related Documents :
19862345 - Experience-driven formation of parts-based representations in a model of layered visual...
18298135 - How the nature of an observation affects single-trajectory entropies.
22099855 - Brain networks in posterior cortical atrophy: a single case tractography study and lite...
20454435 - Class of continuous level associative memory neural nets.
2727215 - Within-channel selection and event-related potentials during selective auditory attention.
17702605 - A novel approach to clinical-radiological correlations: anatomo-clinical overlapping ma...
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't     Date:  2009-07-28
Journal Detail:
Title:  IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council     Volume:  20     ISSN:  1941-0093     ISO Abbreviation:  -     Publication Date:  2009 Sep 
Date Detail:
Created Date:  2009-09-03     Completed Date:  2009-11-04     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101211035     Medline TA:  IEEE Trans Neural Netw     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1463-73     Citation Subset:  IM    
Affiliation:
Institute of Industrial Science, University of Tokyo, Tokyo 153-8505, Japan. gouhei@sat.t.u-tokyo.ac.jp
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Association Learning* / physiology
Color
Computer Simulation
Humans
Image Processing, Computer-Assisted / methods*
Memory* / physiology
Mental Recall / physiology
Neural Networks (Computer)*
Neurons / physiology
Nonlinear Dynamics
Normal Distribution
Periodicity
Probability

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Multiple nuclei tracking using integer programming for quantitative cancer cell cycle analysis.
Next Document:  Multilayer SOM with tree-structured data for efficient document retrieval and plagiarism detection.