Self-Organization of Symmetry Networks: Transformation Invariance from the Spontaneous Symmetry-Breaking Mechanism
Abstract
Symmetry networks use permutation symmetries among synaptic weights to achieve transformation-invariant response. This article proposes a generic mechanism by which such symmetries can develop during unsupervised adaptation: it is shown analytically that spontaneous symmetry breaking can result in the discovery of unknown invariances of the data's probability distribution. It is proposed that a role of sparse coding is to facilitate the discovery of statistical invariances by this mechanism. It is demonstrated that the statistical dependences that exist between simple-cell-like threshold feature detectors, when exposed to temporally uncorrelated natural image data, can drive the development of complex-cell-like invariances, via single-cell Hebbian adaptation. A single learning rule can generate both simple-cell-like and complex-cell-like receptive fields.
Cite
Text
Webber. "Self-Organization of Symmetry Networks: Transformation Invariance from the Spontaneous Symmetry-Breaking Mechanism." Neural Computation, 2000. doi:10.1162/089976600300015718Markdown
[Webber. "Self-Organization of Symmetry Networks: Transformation Invariance from the Spontaneous Symmetry-Breaking Mechanism." Neural Computation, 2000.](https://mlanthology.org/neco/2000/webber2000neco-selforganization/) doi:10.1162/089976600300015718BibTeX
@article{webber2000neco-selforganization,
title = {{Self-Organization of Symmetry Networks: Transformation Invariance from the Spontaneous Symmetry-Breaking Mechanism}},
author = {Webber, Chris J. S.},
journal = {Neural Computation},
year = {2000},
pages = {565-596},
doi = {10.1162/089976600300015718},
volume = {12},
url = {https://mlanthology.org/neco/2000/webber2000neco-selforganization/}
}