A Numerical Method for Frequency Determination in the Astable Cellular Neural Networks with Opposite-Sign Templates

In this study, a numerical method is proposed to determine the oscillation frequencies in the astable cellular neural networks with opposite-sign templates. This method depends on the training of a multilayer perceptron that uses various template coefficients and the correspondant frequency values as inputs and outputs. First of all, a frequency surface is obtained from templates and then, training samples are picked from this surface in order to apply to multilayer perceptron. The effects of the template coefficients to the oscillation frequencies are also investigated. Furthermore, an oscillator design is carried out for simulation and the performance as well as the advantages of the proposed method are evaluated.