Gradient computation in time delayed recurrent neural network with memory for static input-output mapping under tability constraint

Abstract

The complex retinal neural layer in the human visual system is considered to perforin certain early visual processing such as Edge formation, Mach bands and Herrmann grid illusions etc. In this paper we examine how an array of such complex neurons and their associated neural circuitry could be used for static input-output mapping without losing stability. The advantage of using the proposed complex retinal type neural model is that it has a spatio-temporal structure whose transient and steady-state responses provide adequate information for use in image recognition systems. In order to utilize these networks' full capability, it is necessary to adapt the network parameters by computing the g..