Cargando…

Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding

Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent attention has been focused on the development of supervised lea...

Descripción completa

Detalles Bibliográficos
Autores principales: Gardner, Brian, Grüning, André
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4988787/
https://www.ncbi.nlm.nih.gov/pubmed/27532262
http://dx.doi.org/10.1371/journal.pone.0161335
_version_ 1782448475738210304
author Gardner, Brian
Grüning, André
author_facet Gardner, Brian
Grüning, André
author_sort Gardner, Brian
collection PubMed
description Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent attention has been focused on the development of supervised learning rules for spiking neural networks that utilise a temporal coding scheme. However, despite significant progress in this area, there still lack rules that have a theoretical basis, and yet can be considered biologically relevant. Here we examine the general conditions under which synaptic plasticity most effectively takes place to support the supervised learning of a precise temporal code. As part of our analysis we examine two spike-based learning methods: one of which relies on an instantaneous error signal to modify synaptic weights in a network (INST rule), and the other one relying on a filtered error signal for smoother synaptic weight modifications (FILT rule). We test the accuracy of the solutions provided by each rule with respect to their temporal encoding precision, and then measure the maximum number of input patterns they can learn to memorise using the precise timings of individual spikes as an indication of their storage capacity. Our results demonstrate the high performance of the FILT rule in most cases, underpinned by the rule’s error-filtering mechanism, which is predicted to provide smooth convergence towards a desired solution during learning. We also find the FILT rule to be most efficient at performing input pattern memorisations, and most noticeably when patterns are identified using spikes with sub-millisecond temporal precision. In comparison with existing work, we determine the performance of the FILT rule to be consistent with that of the highly efficient E-learning Chronotron rule, but with the distinct advantage that our FILT rule is also implementable as an online method for increased biological realism.
format Online
Article
Text
id pubmed-4988787
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-49887872016-08-29 Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding Gardner, Brian Grüning, André PLoS One Research Article Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent attention has been focused on the development of supervised learning rules for spiking neural networks that utilise a temporal coding scheme. However, despite significant progress in this area, there still lack rules that have a theoretical basis, and yet can be considered biologically relevant. Here we examine the general conditions under which synaptic plasticity most effectively takes place to support the supervised learning of a precise temporal code. As part of our analysis we examine two spike-based learning methods: one of which relies on an instantaneous error signal to modify synaptic weights in a network (INST rule), and the other one relying on a filtered error signal for smoother synaptic weight modifications (FILT rule). We test the accuracy of the solutions provided by each rule with respect to their temporal encoding precision, and then measure the maximum number of input patterns they can learn to memorise using the precise timings of individual spikes as an indication of their storage capacity. Our results demonstrate the high performance of the FILT rule in most cases, underpinned by the rule’s error-filtering mechanism, which is predicted to provide smooth convergence towards a desired solution during learning. We also find the FILT rule to be most efficient at performing input pattern memorisations, and most noticeably when patterns are identified using spikes with sub-millisecond temporal precision. In comparison with existing work, we determine the performance of the FILT rule to be consistent with that of the highly efficient E-learning Chronotron rule, but with the distinct advantage that our FILT rule is also implementable as an online method for increased biological realism. Public Library of Science 2016-08-17 /pmc/articles/PMC4988787/ /pubmed/27532262 http://dx.doi.org/10.1371/journal.pone.0161335 Text en © 2016 Gardner, Grüning http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Gardner, Brian
Grüning, André
Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
title Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
title_full Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
title_fullStr Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
title_full_unstemmed Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
title_short Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
title_sort supervised learning in spiking neural networks for precise temporal encoding
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4988787/
https://www.ncbi.nlm.nih.gov/pubmed/27532262
http://dx.doi.org/10.1371/journal.pone.0161335
work_keys_str_mv AT gardnerbrian supervisedlearninginspikingneuralnetworksforprecisetemporalencoding
AT gruningandre supervisedlearninginspikingneuralnetworksforprecisetemporalencoding