Abstract
Cyclical activities are basic characteristics of all living organisms. Neurobiologists have discovered that a single neuron often possesses membrane properties that yield oscillations. When coupled with other neurons, oscillations with varying properties, depending on the type of interconnection, can be generated. Synchronization and temporal correlation of these oscillations can be utilized in pattern recognition of different objects. The speed of recognition depends on the speed of synchronization. We propose evolutionary coupled neural oscillators to minimize the synchronization time through optimization of the neuron parameters by means of a genetic algorithm (GA). The GA, with its global search capability, finds the optimum neuron parameters through a fitness measure that reflects the correlation strength between oscillators. The trial-and-error process of estimating the neuron parameters is thus avoided. The Gray code gave better results than binary representation. Superiority of the method is demonstrated through an application in character recognition.