Nonlinear Hebbian Learning as a Unifying Principle in Receptive Field Formation
Fig 6
Receptive fields for non-whitened natural images.
(a-i) Receptive field obtained for network simulations with the quadratic rectifier (top), linear rectifier (center) and L0 sparse coding (bottom). For few neurons (left and center), the principal components dominate the optimization and receptive fields are nonlocal, since they extend over most of the image patch. For an overcomplete network with 1000 neurons (right), lateral inhibition promotes diversity of receptive fields, including more localized ones. (insets) Sample receptive fields developed for each simulation.