Symmetry perception with spiking neural networks

Abstract Mirror symmetry is an abundant feature in both nature and technology. Its successful detection is critical for perception procedures based on visual stimuli and requires organizational processes. Neuromorphic computing, utilizing brain-mimicked networks, could be a technology-solution provi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jonathan K. George, Cesare Soci, Mario Miscuglio, Volker J. Sorger
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/ce865bbdcd094b12b89bb3d25781aeba
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ce865bbdcd094b12b89bb3d25781aeba
record_format	dspace
spelling	oai:doaj.org-article:ce865bbdcd094b12b89bb3d25781aeba2021-12-02T13:34:46ZSymmetry perception with spiking neural networks10.1038/s41598-021-85232-32045-2322https://doaj.org/article/ce865bbdcd094b12b89bb3d25781aeba2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85232-3https://doaj.org/toc/2045-2322Abstract Mirror symmetry is an abundant feature in both nature and technology. Its successful detection is critical for perception procedures based on visual stimuli and requires organizational processes. Neuromorphic computing, utilizing brain-mimicked networks, could be a technology-solution providing such perceptual organization functionality, and furthermore has made tremendous advances in computing efficiency by applying a spiking model of information. Spiking models inherently maximize efficiency in noisy environments by placing the energy of the signal in a minimal time. However, many neuromorphic computing models ignore time delay between nodes, choosing instead to approximate connections between neurons as instantaneous weighting. With this assumption, many complex time interactions of spiking neurons are lost. Here, we show that the coincidence detection property of a spiking-based feed-forward neural network enables mirror symmetry. Testing this algorithm exemplary on geospatial satellite image data sets reveals how symmetry density enables automated recognition of man-made structures over vegetation. We further demonstrate that the addition of noise improves feature detectability of an image through coincidence point generation. The ability to obtain mirror symmetry from spiking neural networks can be a powerful tool for applications in image-based rendering, computer graphics, robotics, photo interpretation, image retrieval, video analysis and annotation, multi-media and may help accelerating the brain-machine interconnection. More importantly it enables a technology pathway in bridging the gap between the low-level incoming sensor stimuli and high-level interpretation of these inputs as recognized objects and scenes in the world.Jonathan K. GeorgeCesare SociMario MiscuglioVolker J. SorgerNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jonathan K. George Cesare Soci Mario Miscuglio Volker J. Sorger Symmetry perception with spiking neural networks
description	Abstract Mirror symmetry is an abundant feature in both nature and technology. Its successful detection is critical for perception procedures based on visual stimuli and requires organizational processes. Neuromorphic computing, utilizing brain-mimicked networks, could be a technology-solution providing such perceptual organization functionality, and furthermore has made tremendous advances in computing efficiency by applying a spiking model of information. Spiking models inherently maximize efficiency in noisy environments by placing the energy of the signal in a minimal time. However, many neuromorphic computing models ignore time delay between nodes, choosing instead to approximate connections between neurons as instantaneous weighting. With this assumption, many complex time interactions of spiking neurons are lost. Here, we show that the coincidence detection property of a spiking-based feed-forward neural network enables mirror symmetry. Testing this algorithm exemplary on geospatial satellite image data sets reveals how symmetry density enables automated recognition of man-made structures over vegetation. We further demonstrate that the addition of noise improves feature detectability of an image through coincidence point generation. The ability to obtain mirror symmetry from spiking neural networks can be a powerful tool for applications in image-based rendering, computer graphics, robotics, photo interpretation, image retrieval, video analysis and annotation, multi-media and may help accelerating the brain-machine interconnection. More importantly it enables a technology pathway in bridging the gap between the low-level incoming sensor stimuli and high-level interpretation of these inputs as recognized objects and scenes in the world.
format	article
author	Jonathan K. George Cesare Soci Mario Miscuglio Volker J. Sorger
author_facet	Jonathan K. George Cesare Soci Mario Miscuglio Volker J. Sorger
author_sort	Jonathan K. George
title	Symmetry perception with spiking neural networks
title_short	Symmetry perception with spiking neural networks
title_full	Symmetry perception with spiking neural networks
title_fullStr	Symmetry perception with spiking neural networks
title_full_unstemmed	Symmetry perception with spiking neural networks
title_sort	symmetry perception with spiking neural networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/ce865bbdcd094b12b89bb3d25781aeba
work_keys_str_mv	AT jonathankgeorge symmetryperceptionwithspikingneuralnetworks AT cesaresoci symmetryperceptionwithspikingneuralnetworks AT mariomiscuglio symmetryperceptionwithspikingneuralnetworks AT volkerjsorger symmetryperceptionwithspikingneuralnetworks
_version_	1718392761829294080

Symmetry perception with spiking neural networks

Ejemplares similares