Responses of direction-selective neurons in cat striate cortex (area 17) were studied with flashed-bar stimuli. Spatial parameters of interactions within the receptive field giving rise to direction selectivity and of receptive-field subunits were quantitatively determined for the same cells and correlated. A bar stimulus flashed sequentially at two nearby locations in the receptive field produced direction-selective behavior comparable with that elicited by continuously moving stimuli. Each cell exhibited a characteristic optimal spatial displacement, Dopt, for which responses in the presumed preferred and null directions were maximally distinct. In all cases, Dopt was much smaller than the receptive-field size. The spatial structure of receptive fields in simple cells was studied using single narrow-bar stimuli flashed at different locations in the receptive field. The resulting line-weighting function exhibited alternating regions of ON and OFF responses having a characteristic spatial period or wavelength, lambda. Spatial subunit structure in complex cells was determined by flashing two bars simultaneously in the receptive field. The response as a function of bar separation was again a wavelike function having a spatial wavelength, lambda. Values of the optimal displacement for direction selectivity, Dopt, showed a clear relationship with the spatial wavelength, lambda, for a given unit. Dopt was also correlated to a somewhat lesser degree with receptive-field size. Generally, the ratio of Dopt to lambda was approximately 1/10 to 1/4, in agreement with theoretical predictions by Marr and Poggio. Taken together with the findings of Movshon et al., these results indicate a systematic relationship between Dopt and the spatial frequency of a sinusoidal grating, which is optimal for that cell. Such a relationship is consistent with the results of human psychophysical experiments on apparent motion.
Receptive Field Size Optimization with Continuous Time Pooling
