A model for centering visual stimuli through adaptive value learning

Abstract

Learning through adaptive value leads to environment-dependent behaviors. This paper introduces a model for stimuli centering within a visual field following the principles of this kind of learning. The neurons responsible for the eye movement execute a mapping of the visual field by means of the adaptive value of each movement. This value is the result of the interaction of biologically inspired layers, chosen in an evolutionarily and without any planning or supervision, throughout the learning process. To check the stabilization and learning abilities of the model three measurements have been used: an energy function representing weight variations; a measurement of the increment of the distances through the chosen trajectories; and, a discriminant linear analysis of the model behavior.