Lippert, J., Fleet, D.J., and Wagner, H.
Development of Disparity Tuning as Simulated by a Neural Net: Response
Characteristics of Output.
Biological Cybernetics, 83(1):61--72, 2000
Previous research has suggested that the processing
of binocular disparity in complex cells may be described with an
energy formalism. The energy formalism allows for a representation of
disparity by differences in the position or in the phase of monocular
receptive subfields of binocular cells, or by combination of these two
types. We studied the coding of disparities with an approach
complementary to previous algorithmic investigations. Since
realization of these representations is probably not genetically
determined, but learned during ontogeny, we used backpropagation
networks to study which of these three possibilities were realized
within neural nets. Three types of networks were trained with noise
patterns in analogy to the three types of energy models. The networks
learned the task and generalized to untrained correlated noise pattern
input. Outputs were broadly tuned to spatial frequency and did not
respond to anti-correlated noise patterns. Although the energy model
was not implemented, we could analyze the outputs of the networks
using predictions of the energy formalism. After learning was
completed the model neurons prefered position shifts over phase shifts
in representing disparity. We discuss the general meaning of these
findings and correspondences and deviations between the energy model
and our networks.
Return to David Fleet's home page.