How lateral connections and spiking dynamics may separate multiple objects moving together.

Over successive stages, the ventral visual system of the primate brain develops neurons that respond selectively to particular objects or faces with translation, size and view invariance. The powerful neural representations found in Inferotemporal cortex form a remarkably rapid and robust basis for...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Benjamin D Evans, Simon M Stringer
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2013
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/bd768e793e774280a7755d4cb89b07e0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bd768e793e774280a7755d4cb89b07e0
record_format	dspace
spelling	oai:doaj.org-article:bd768e793e774280a7755d4cb89b07e02021-11-18T09:01:33ZHow lateral connections and spiking dynamics may separate multiple objects moving together.1932-620310.1371/journal.pone.0069952https://doaj.org/article/bd768e793e774280a7755d4cb89b07e02013-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/23936362/?tool=EBIhttps://doaj.org/toc/1932-6203Over successive stages, the ventral visual system of the primate brain develops neurons that respond selectively to particular objects or faces with translation, size and view invariance. The powerful neural representations found in Inferotemporal cortex form a remarkably rapid and robust basis for object recognition which belies the difficulties faced by the system when learning in natural visual environments. A central issue in understanding the process of biological object recognition is how these neurons learn to form separate representations of objects from complex visual scenes composed of multiple objects. We show how a one-layer competitive network comprised of 'spiking' neurons is able to learn separate transformation-invariant representations (exemplified by one-dimensional translations) of visual objects that are always seen together moving in lock-step, but separated in space. This is achieved by combining 'Mexican hat' functional lateral connectivity with cell firing-rate adaptation to temporally segment input representations of competing stimuli through anti-phase oscillations (perceptual cycles). These spiking dynamics are quickly and reliably generated, enabling selective modification of the feed-forward connections to neurons in the next layer through Spike-Time-Dependent Plasticity (STDP), resulting in separate translation-invariant representations of each stimulus. Variations in key properties of the model are investigated with respect to the network's ability to develop appropriate input representations and subsequently output representations through STDP. Contrary to earlier rate-coded models of this learning process, this work shows how spiking neural networks may learn about more than one stimulus together without suffering from the 'superposition catastrophe'. We take these results to suggest that spiking dynamics are key to understanding biological visual object recognition.Benjamin D EvansSimon M StringerPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 8, Iss 8, p e69952 (2013)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Benjamin D Evans Simon M Stringer How lateral connections and spiking dynamics may separate multiple objects moving together.
description	Over successive stages, the ventral visual system of the primate brain develops neurons that respond selectively to particular objects or faces with translation, size and view invariance. The powerful neural representations found in Inferotemporal cortex form a remarkably rapid and robust basis for object recognition which belies the difficulties faced by the system when learning in natural visual environments. A central issue in understanding the process of biological object recognition is how these neurons learn to form separate representations of objects from complex visual scenes composed of multiple objects. We show how a one-layer competitive network comprised of 'spiking' neurons is able to learn separate transformation-invariant representations (exemplified by one-dimensional translations) of visual objects that are always seen together moving in lock-step, but separated in space. This is achieved by combining 'Mexican hat' functional lateral connectivity with cell firing-rate adaptation to temporally segment input representations of competing stimuli through anti-phase oscillations (perceptual cycles). These spiking dynamics are quickly and reliably generated, enabling selective modification of the feed-forward connections to neurons in the next layer through Spike-Time-Dependent Plasticity (STDP), resulting in separate translation-invariant representations of each stimulus. Variations in key properties of the model are investigated with respect to the network's ability to develop appropriate input representations and subsequently output representations through STDP. Contrary to earlier rate-coded models of this learning process, this work shows how spiking neural networks may learn about more than one stimulus together without suffering from the 'superposition catastrophe'. We take these results to suggest that spiking dynamics are key to understanding biological visual object recognition.
format	article
author	Benjamin D Evans Simon M Stringer
author_facet	Benjamin D Evans Simon M Stringer
author_sort	Benjamin D Evans
title	How lateral connections and spiking dynamics may separate multiple objects moving together.
title_short	How lateral connections and spiking dynamics may separate multiple objects moving together.
title_full	How lateral connections and spiking dynamics may separate multiple objects moving together.
title_fullStr	How lateral connections and spiking dynamics may separate multiple objects moving together.
title_full_unstemmed	How lateral connections and spiking dynamics may separate multiple objects moving together.
title_sort	how lateral connections and spiking dynamics may separate multiple objects moving together.
publisher	Public Library of Science (PLoS)
publishDate	2013
url	https://doaj.org/article/bd768e793e774280a7755d4cb89b07e0
work_keys_str_mv	AT benjamindevans howlateralconnectionsandspikingdynamicsmayseparatemultipleobjectsmovingtogether AT simonmstringer howlateralconnectionsandspikingdynamicsmayseparatemultipleobjectsmovingtogether
_version_	1718421046534602752

How lateral connections and spiking dynamics may separate multiple objects moving together.

Ejemplares similares