Cargando…

Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task

Neural networks with a single plastic layer employing reward modulated spike time dependent plasticity (STDP) are capable of learning simple foraging tasks. Here we demonstrate advanced pattern discrimination and continuous learning in a network of spiking neurons with multiple plastic layers. The n...

Descripción completa

Detalles Bibliográficos
Autores principales: Sanda, Pavel, Skorheim, Steven, Bazhenov, Maxim
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5636167/
https://www.ncbi.nlm.nih.gov/pubmed/28961245
http://dx.doi.org/10.1371/journal.pcbi.1005705
_version_ 1783270400174587904
author Sanda, Pavel
Skorheim, Steven
Bazhenov, Maxim
author_facet Sanda, Pavel
Skorheim, Steven
Bazhenov, Maxim
author_sort Sanda, Pavel
collection PubMed
description Neural networks with a single plastic layer employing reward modulated spike time dependent plasticity (STDP) are capable of learning simple foraging tasks. Here we demonstrate advanced pattern discrimination and continuous learning in a network of spiking neurons with multiple plastic layers. The network utilized both reward modulated and non-reward modulated STDP and implemented multiple mechanisms for homeostatic regulation of synaptic efficacy, including heterosynaptic plasticity, gain control, output balancing, activity normalization of rewarded STDP and hard limits on synaptic strength. We found that addition of a hidden layer of neurons employing non-rewarded STDP created neurons that responded to the specific combinations of inputs and thus performed basic classification of the input patterns. When combined with a following layer of neurons implementing rewarded STDP, the network was able to learn, despite the absence of labeled training data, discrimination between rewarding patterns and the patterns designated as punishing. Synaptic noise allowed for trial-and-error learning that helped to identify the goal-oriented strategies which were effective in task solving. The study predicts a critical set of properties of the spiking neuronal network with STDP that was sufficient to solve a complex foraging task involving pattern classification and decision making.
format Online
Article
Text
id pubmed-5636167
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-56361672017-10-30 Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task Sanda, Pavel Skorheim, Steven Bazhenov, Maxim PLoS Comput Biol Research Article Neural networks with a single plastic layer employing reward modulated spike time dependent plasticity (STDP) are capable of learning simple foraging tasks. Here we demonstrate advanced pattern discrimination and continuous learning in a network of spiking neurons with multiple plastic layers. The network utilized both reward modulated and non-reward modulated STDP and implemented multiple mechanisms for homeostatic regulation of synaptic efficacy, including heterosynaptic plasticity, gain control, output balancing, activity normalization of rewarded STDP and hard limits on synaptic strength. We found that addition of a hidden layer of neurons employing non-rewarded STDP created neurons that responded to the specific combinations of inputs and thus performed basic classification of the input patterns. When combined with a following layer of neurons implementing rewarded STDP, the network was able to learn, despite the absence of labeled training data, discrimination between rewarding patterns and the patterns designated as punishing. Synaptic noise allowed for trial-and-error learning that helped to identify the goal-oriented strategies which were effective in task solving. The study predicts a critical set of properties of the spiking neuronal network with STDP that was sufficient to solve a complex foraging task involving pattern classification and decision making. Public Library of Science 2017-09-29 /pmc/articles/PMC5636167/ /pubmed/28961245 http://dx.doi.org/10.1371/journal.pcbi.1005705 Text en © 2017 Sanda et al 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
Sanda, Pavel
Skorheim, Steven
Bazhenov, Maxim
Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task
title Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task
title_full Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task
title_fullStr Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task
title_full_unstemmed Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task
title_short Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task
title_sort multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5636167/
https://www.ncbi.nlm.nih.gov/pubmed/28961245
http://dx.doi.org/10.1371/journal.pcbi.1005705
work_keys_str_mv AT sandapavel multilayernetworkutilizingrewardedspiketimedependentplasticitytolearnaforagingtask
AT skorheimsteven multilayernetworkutilizingrewardedspiketimedependentplasticitytolearnaforagingtask
AT bazhenovmaxim multilayernetworkutilizingrewardedspiketimedependentplasticitytolearnaforagingtask