Analysis of the two-dimensional receptive fields learned by the Generalized Hebbian Algorithm in response to random input

摘要

The Generalized Hebbian Algorithm has been proposed for training linear feedforward neural networks and has been proven to cause the weights to converge to the eigenvectors of the input distribution (Sanger 1989a, b). For an input distribution given by 2D Gaussian smoothed white noise inside a Gaussian window, some of the masks learned by the Generalized Hebbian Algorithm resemble edge and bar detectors. Since these do not match the form of the actual eigenvectors of this distribution (Linsker 1987, 1990), we seek an explanation of the development of the masks prior to complete convergence to the correct solution. Analysis in the spatial and spatial frequency domains sheds light on this development, and shows that the masks which occur tend to be localized in the spatial frequency domain, reminiscent of one of the properties of 2D Gabor filters proposed by Daugman ( 1980, 1985) as a model for the receptive fields of cells in primate visual cortex.