An Evolutionary Coupled Neural Oscillators with Application to Pattern Recognition
Cyclical activities are basic characteristics of all living organisms. Neurobiologists have discovered that a single neuron often possesses membrane properties that are responsible for the generation of oscillations. When coupled with other neurons, oscillations with varying properties depending on...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2001-01-01
|
Series: | Journal of King Saud University: Engineering Sciences |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1018363918307359 |
id |
doaj-0e2bc6f2fc44499bb030c8bb2b17f14d |
---|---|
record_format |
Article |
spelling |
doaj-0e2bc6f2fc44499bb030c8bb2b17f14d2020-11-25T02:37:29ZengElsevierJournal of King Saud University: Engineering Sciences1018-36392001-01-01132227236An Evolutionary Coupled Neural Oscillators with Application to Pattern RecognitionA. Tobal0K. Mahar1College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia, E-mail: atoba@ccisksu.edusaComputer Engineering Dept., College of Engineering and Technology, Arab Academy for Science and Technology, Alexandria, P.O.Box 1029, Egypt, E-mail: khmahar@aast.eduCyclical activities are basic characteristics of all living organisms. Neurobiologists have discovered that a single neuron often possesses membrane properties that are responsible for the generation of oscillations. When coupled with other neurons, oscillations with varying properties depending on the type of interconnection can be generated. Using synchronization and temporal correlation of these oscillations can cany out the tasks of pattern recognition of different objects. The speed of recognition depends on the speed of synchronization. In this paper, we propose evolutionary coupled neural oscillators to minimize the time of synchronization through the optimization of the neuron parameters by means of a genetic algorithm. The genetic algorithm, with its global search capability, finds the optimum neuron parameters through a fitness measure that reflects the correlation strength between oscillators. Thus avoiding the trial-and-error process of estimating the neuron parameters. The superiority of the method is demonstrated through an application of character recognition process.http://www.sciencedirect.com/science/article/pii/S1018363918307359 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
A. Tobal K. Mahar |
spellingShingle |
A. Tobal K. Mahar An Evolutionary Coupled Neural Oscillators with Application to Pattern Recognition Journal of King Saud University: Engineering Sciences |
author_facet |
A. Tobal K. Mahar |
author_sort |
A. Tobal |
title |
An Evolutionary Coupled Neural Oscillators with Application to Pattern Recognition |
title_short |
An Evolutionary Coupled Neural Oscillators with Application to Pattern Recognition |
title_full |
An Evolutionary Coupled Neural Oscillators with Application to Pattern Recognition |
title_fullStr |
An Evolutionary Coupled Neural Oscillators with Application to Pattern Recognition |
title_full_unstemmed |
An Evolutionary Coupled Neural Oscillators with Application to Pattern Recognition |
title_sort |
evolutionary coupled neural oscillators with application to pattern recognition |
publisher |
Elsevier |
series |
Journal of King Saud University: Engineering Sciences |
issn |
1018-3639 |
publishDate |
2001-01-01 |
description |
Cyclical activities are basic characteristics of all living organisms. Neurobiologists have discovered that a single neuron often possesses membrane properties that are responsible for the generation of oscillations. When coupled with other neurons, oscillations with varying properties depending on the type of interconnection can be generated. Using synchronization and temporal correlation of these oscillations can cany out the tasks of pattern recognition of different objects. The speed of recognition depends on the speed of synchronization. In this paper, we propose evolutionary coupled neural oscillators to minimize the time of synchronization through the optimization of the neuron parameters by means of a genetic algorithm. The genetic algorithm, with its global search capability, finds the optimum neuron parameters through a fitness measure that reflects the correlation strength between oscillators. Thus avoiding the trial-and-error process of estimating the neuron parameters. The superiority of the method is demonstrated through an application of character recognition process. |
url |
http://www.sciencedirect.com/science/article/pii/S1018363918307359 |
work_keys_str_mv |
AT atobal anevolutionarycoupledneuraloscillatorswithapplicationtopatternrecognition AT kmahar anevolutionarycoupledneuraloscillatorswithapplicationtopatternrecognition AT atobal evolutionarycoupledneuraloscillatorswithapplicationtopatternrecognition AT kmahar evolutionarycoupledneuraloscillatorswithapplicationtopatternrecognition |
_version_ |
1724795293244850176 |