Some Learning Models of Visual System Based on Local Sensory Signals Integration Learning

Our visual system has many interesting abilities like vestibulo-ocular reflex. These abilities are helpful for us to perceive the environment effectively and often have adaptability to the environment. On the other way, LSSI (Local Sensory Signals Integration) learning base on the smoothness of the relation between the spatial and temporal information, has been already proposed. In this paper, some computational learning models, each of which is extension of the LSSI learning, are proposed. Some of the abilities of our visual system, those are head invariant perception, vestibulo-ocular reflex and smooth pursuit eye movements, are tried to be explained by those models. Basic functions are realized in some simulations using those models.