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

@article{Olshausen1996EmergenceOS,
  title={Emergence of simple-cell receptive field properties by learning a sparse code for natural images},
  author={Bruno A. Olshausen and David J. Field},
  journal={Nature},
  year={1996},
  volume={381},
  pages={607-609}
}
THE receptive fields of simple cells in mammalian primary visual cortex can be characterized as being spatially localized, oriented1–4 and bandpass (selective to structure at different spatial scales), comparable to the basis functions of wavelet transforms5,6. [] Key Result The resulting sparse image code provides a more efficient representation for later stages of processing because it possesses a higher degree of statistical independence among its outputs.

Development of localized oriented receptive fields by learning a translation-invariant code for natural images.

TLDR
It is shown that a strategy for transformation-invariant coding of images based on a first-order Taylor series expansion of an image also causes localized, oriented receptive fields to be learned from natural image inputs.

Are sparse-coding simple cell receptive field models physiologically plausible?

  • P. Watters
  • Biology
    Journal of integrative neuroscience
  • 2006
TLDR
Across all image themes, basis function sizes, number of basis functions, sparseness factors and learning rates, the spatial-frequency tuning did not closely resemble that of primate area 17 -- the model results more closely resembled the unclassified cat neurones of area 19 with a single exception, and not area 17 as predicted.

Sparse coding models predict a spectral bias in the development of primary visual cortex (V1) receptive fields

TLDR
This work trains an overcomplete sparse coding model (Sparsenet) on natural images and finds that there is indeed order in the development of its basis functions, with basis functions tuned to lower spatial frequencies emerging earlier and higher spatial frequency basis functions emerging later.

Emergence of complex cell properties by learning to generalize in natural scenes

TLDR
A model in which neural activity encodes the probability distribution most consistent with a given image is presented, which provides a new functional explanation for nonlinear effects in complex cells and offers insight into coding strategies in primary visual cortex (V1) and higher visual areas.

Efficient Encoding of Natural Time Varying Images Produces Oriented Space-Time Receptive Fields

TLDR
An artificial neural network is described that attempts to accurately reconstruct its spatiotemporal input data while simultaneously reducing the statistical dependencies between its outputs.

Finding the optimal sparse, overcomplete model for natural images by model selection

TLDR
The goal of this work is to investigate the claim that sparse, overcomplete codes might lend some computational advantage in the processing of visual information.

Hierarchical Learning from Natural Images

In this paper, we apply unsupervised learning methods to construct response functions for V1 simple cells, V1 complex cells, and V2 simple cells from a set of natural images. To support this, we

Localized Receptive Fields May Mediate Transformation-Invariant Recognition in the Visual Cortex

TLDR
It is shown that a relatively simple neural solution to the problem of transformation-invariant visual recognition also causes localized, oriented receptive fields to be learned from natural images.
...

References

SHOWING 1-10 OF 21 REFERENCES

Relations between the statistics of natural images and the response properties of cortical cells.

  • D. Field
  • Computer Science
    Journal of the Optical Society of America. A, Optics and image science
  • 1987
TLDR
The results obtained with six natural images suggest that the orientation and the spatial-frequency tuning of mammalian simple cells are well suited for coding the information in such images if the goal of the code is to convert higher-order redundancy into first- order redundancy.

Entropy reduction and decorrelation in visual coding by oriented neural receptive fields

  • J. Daugman
  • Computer Science, Biology
    IEEE Transactions on Biomedical Engineering
  • 1989
TLDR
The present image coding simulations, based on quantitative neurobiological data about the code primitives, provide measures of the bit-rate efficiency of such oriented, quadrature, neural codes.

What Is the Goal of Sensory Coding?

  • D. Field
  • Computer Science
    Neural Computation
  • 1994
TLDR
It is proposed that compact coding schemes are insufficient to account for the receptive field properties of cells in the mammalian visual pathway and suggested that natural scenes, to a first approximation, can be considered as a sum of self-similar local functions (the inverse of a wavelet).

An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex.

TLDR
It seems that an optimal strategy has evolved for sampling images simultaneously in the 2D spatial and spatial frequency domains and the Gabor function provides a useful and reasonably accurate description of most spatial aspects of simple receptive fields.

Finding compact and sparse-distributed representations of visual images

TLDR
An artificial neural network which self-organizes on the basis of simple Hebbian learning and negative feedback of activation is introduced and it is shown that it is capable both of forming compact codings of data distributions and of identifying filters most sensitive to sparse-distributed codes.

Formation of receptive fields in realistic visual environments according to the Bienenstock, Cooper, and Munro (BCM) theory.

  • C. C. LawL. Cooper
  • Biology
    Proceedings of the National Academy of Sciences of the United States of America
  • 1994
The Bienenstock, Cooper, and Munro (BCM) theory of synaptic plasticity has successfully reproduced the development of orientation selectivity and ocular dominance in kitten visual cortex in normal,

Real and optimal neural images in early vision

TLDR
Compared neural images obtained by scanning an image while recording from a second-order neuron in the fly visual system are compared with theoretical calculations based on maximizing information, taking into account the statistical structure of natural images.

Two-dimensional spatial structure of receptive fields in monkey striate cortex.

  • A. ParkerM. Hawken
  • Biology, Psychology
    Journal of the Optical Society of America. A, Optics and image science
  • 1988
Measurements of the spatial contrast sensitivity function and orientation selectivity of visual neurons in the foveal striate cortex (V1) of primates were interpreted within the context of a model of

The statistics of natural images

Recently there has been a resurgence of interest in the properties of natural images. Their statistics are important not only in image compression but also for the study of sensory processing in