A Recurrent Neural Network for Generation of Occular Saccades

This paper presents a neural network able to control saccadic movements. The input to the network is a specification of a stimulation site on the collicular motor map. The output is the time course of the eye position in the orbit (horizontal and vertical angles). The units in the network exhibit a one-to-one correspondance with neurons in the intermediate layer of the superior colliculus (collicular motor map), in the brainstem and with oculomotor neurons. Simulations carried out with this network demonstrate its ability to reproduce in a straightforward fashion many experimental observations.