The Identification of Features in Artificial Data and the Formation of Local Filters From Video Data Using the Rectified Gaussian Distribution.

Abstract

We investigate the use of an unsupervised artificial neural network to form a sparse representation of the underlying causes in a data set. By using fixed lateral connections that are derived from the Rectified Generalised Gaussian distribution, we form a network that is capable of identifying multiple cause structure in visual data and grouping similar causes together on the output response of the network. We show that the network may be used to form local spatiotemporal filters in response to real images contained in video data.