A self-organizing model of perisaccadic visual receptive field dynamics in primate visual and oculomotor system

Abstract

We propose and examine a model for how perisaccadic visual receptive field dynamics, observed in a range of primate brain areas such as LIF, FEF SC, V3, V3A, V2, and V1, may develop through a biologically plausible process of unsupervised visually guided learning. These dynamics are associated with remapping, which is the phenomenon where receptive fields anticipate the consequences of saccadic eye movements. We find that a neural network model using a local associative synaptic learning rule, when exposed to visual scenes in conjunction with saccades, can account for a range of associated phenomena. In particular, our model demonstrates predictive and pre-saccadic remapping, responsiveness shifts around the time of saccades, and remapping from multiple directions.