A study on WTA cellular neural networks

Abstract

SUMMARYThis paper addresses a number of basic issues concerning the dynamics of a class of winner-takeall cellular neural networks (WTA CNNs) proposed by Seiler and Nossek. The main result is an analytical estimate for the settling time, which shows from a theoretical point of view that such CNNs are well suited for on-line applications requiring a large number of units, fast processing speed and a relatively high resolution. Other results are the determination of the largest parameter set that guarantee a correct WTA functionality for all initial conditions and the solution of a conjecture made by Seiler and Nossek. These results are proved by means of a new Lyapunov function to analyse the global dynamical behaviour of the WTA CNNs.

Cellular Neural Networks With Virtual Template Expansion for Retinal Vessel Segmentation

“…Taking into account the rather small number of inputs (twelve), the existing chips allow high speed and precision. In principle, the WTA function could be realized also using a CNN [16] even if, to the best of our knowledge, no tested prototype is available. Subtraction of and thresholding can be easily obtained using , and the bias , where is the threshold.…”