We applied a novel ‘white-noise’-like stimulation technique to study the neural circuitry underlying the orientation tuning of simple cortical cells in cats and monkeys. We generate an image sequence (the stimulus) by selecting, at each refresh time, a random image from a finite set s of orthonormal images. For simple cells, we have shown that the above stimulus allows one to compute the projection of the receptive field onto the subspace spanned by the vectors in s (Ringach et al, 1996 ARVO Proceedings in press). The calculation is based on the cross-correlation between the input image sequence and the cell's spike train output. In the present study, we selected s to be the subspace spanned by sine-wave gratings having a fixed spatial frequency but different orientations and spatial phases. A finite orthonormal basis for this subspace is a subset of the complete two-dimensional discrete Hartley basis functions. The choice of this ‘orientation-subspace’ allowed us to measure how the orientation tuning of the cells evolved in time at a particular spatial frequency. In addition to a sharp peak of activity at the optimal orientation of the cell, we observed secondary peaks of the orientation tuning curve at off-optimal orientations. Off-peak inhibition was also observed frequently. These results are difficult to reconcile with feedforward models of the neural network producing orientation tuning, but are consistent with recurrent cortical network models (Carandini and Ringach, 1996, paper presented at the Computation and Neural Systems Conference).
