Analog CMOS implementation of cellular neural networks

Abstract

An analog CMOS circuit realization of cellular neural networks with transconductance elements is presented in this thesis. This realization can be easily adapted to various types of applications in image processing by just choosing the appropriate transconductance parameters according to the predetermined coefficients. The noise-reduction and edge detection examples have shown the effectiveness of the designed networks in real time image processing applications. For “fix function” cellular neural network circuits the number of transistors are reduced further by a new multi-input voltage-controlled current source.