A 2-DIMENSIONAL ENSEMBLE CODING MODEL FOR SPATIAL-TEMPORAL TRANSFORMATION OF SACCADES IN MONKEY SUPERIOR COLLICULUS

Fast saccadic eye movements result from the recruitment of a large population of cells in the midbrain superior colliculus (SC). The SC transmit its output. which desired vectorial eye displacement in a topographically organized motor map, to horizontal and vertical eye velocity generators in the brainstem. It is generally agreed, that saccade generation is under continuous feedback control. An important problem for models of the saccadic system is, how the spatial representation of the SC output is transformed into the temporal code of brainstem cell populations. This problem is even more intriguing, when the possibilty is considered of a dynamic feedback loop which includes the SC. Recent experimental findings support such a possibility. In this paper we analyse the properties of a two-dimensional neural network model for the monkey SC, which incorporates a number of realistic features known from neurophysiology and, in addition, is part of the dynamic feedback loop for generation. Our analysis suggests that the feedback should be organized topographically in order to generate goal-directed saccades. Despite the fact that the neurons in our model are linear, several nonlinear properties of saccades, such as their main-sequence characteristic, as well as saccade averaging to electrical double stimulation can be explained on the basis of the model's architecture.