Refereed full papers (journals, book chapters, international conferences)

1996

@article{OlF1996,
	vgclass =	{refpap},
	author =	{B. A. Olshausen and D. J. Field},
	title =	{Natural image statistics and efficient coding},
	journal =	{Neural Computation},
	volume =	{7},
	number =	{2},
	pages =	{333--339},
	month =	{May},
	year =	{1996},
	abstract =	{Natural images contain characteristic statistical
	regularities that set them apart from purely random images.
	Understanding what these regularities are can enable natural images to
	be coded more efficiently. In this paper, we describe some of the forms
	of structure that are contained in natural images, and we show how
	these are related to the response properties of neurons at early stages
	of the visual system. Many of the important forms of structure require
	higher-order (i.e. more than linear, pairwise) statistics to
	characterize, which makes models based on linear Hebbian learning, or
	principal components analysis, inappropriate for finding efficient
	codes for natural images. We suggest that a good objective for an
	efficient coding of natural scenes is to maximize the sparseness of the
	representation, and we show that a network that learns sparse codes of
	natural scenes succeeds in developing localized, oriented, bandpass
	receptive fields similar to those in the mammalian striate cortex.},
}