[PDF][PDF] Emergence of simple-cell receptive field properties by learning a sparse code for natural images

BA Olshausen - Nature, 1996 - cns.nyu.edu
THE receptive fields of simple cells in mammalian primary visual cortex can be
characterized as being spatially localized, oriented “4 and bandpass (selective to structure
at different spatial scales), comparable to the basis functions of wavelet transforms “. One ...

[HTML][HTML] The “independent components” of natural scenes are edge filters

AJ Bell, TJ Sejnowski - Vision research, 1997 - Elsevier
It has previously been suggested that neurons with line and edge selectivities found in
primary visual cortex of cats and monkeys form a sparse, distributed representation of
natural scenes, and it has been reasoned that such responses should emerge from an ...

[PDF][PDF] Wavelet-like receptive elds emerge from a network that learns sparse codes for natural images.

BA Olshausen, DJ Field - Nature, 1996 - researchgate.net
The spatial receptive elds of simple cells in mammalian striate cortex have been reasonably
well described physiologically 1, 2, 3, 4] and can be characterized as being localized,
oriented, and bandpass (selective to structure at di erent spatial scales), comparable to ...

[HTML][HTML] Sparse coding with an overcomplete basis set: A strategy employed by V1?

BA Olshausen, DJ Field - Vision research, 1997 - Elsevier
The spatial receptive fields of simple cells in mammalian striate cortex have been
reasonably well described physiologically and can be characterized as being localized,
oriented, and bandpass, comparable with the basis functions of wavelet transforms. ...

Natural image statistics and efficient coding

BA Olshausen, DJ Field - Network: computation in neural systems, 1996 - Taylor & Francis
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 ...

What is the goal of sensory coding?

DJ Field - Neural computation, 1994 - MIT Press
Although we know a great deal about how sensory systems code information, there remains
considerable debate regarding the goal of this coding. In many studies, there is an implicit
assumption that there is no single goal. It is assumed that sensory systems solve a wide ...

[CITATION][C] W avelet-like receptive fields em erge from

[CITATION][C] Possible principles underlying the transformations of sensory messages

HB Barlow - 1961 - citeulike.org
Search all the public and authenticated articles in CiteULike. Include unauthenticated results
too (may include "spam") Enter a search phrase. You can also specify a CiteULike article id
(123456),. a DOI (doi:10.1234/12345678). or a PubMed ID (pmid:12345678). ...

Learning efficient linear codes for natural images: the roles of sparseness, overcompleteness, and statistical independence

BA Olshausen, DJ Field - Electronic …, 1996 - proceedings.spiedigitallibrary.org
abstract An algorithm is described which allows for the learning of sparse, overcomplete
image representations. Images are modeled as a linear superposition of basis functions,
and a set of basis functions is sought which maximizes the sparseness of the ...

Independent component filters of natural images compared with simple cells in primary visual cortex

JH van Hateren… - … of the Royal …, 1998 - rspb.royalsocietypublishing.org
Abstract Properties of the receptive fields of simple cells in macaque cortex were compared
with properties of independent component filters generated by independent component
analysis (ICA) on a large set of natural images. Histograms of spatial frequency bandwidth ...