A bio-inspired bistable recurrent cell allows for long-lasting memory.

Recurrent neural networks (RNNs) provide state-of-the-art performances in a wide variety of tasks that require memory. These performances can often be achieved thanks to gated recurrent cells such as gated recurrent units (GRU) and long short-term memory (LSTM). Standard gated cells share a layer in...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Nicolas Vecoven, Damien Ernst, Guillaume Drion
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/9565af3b3b774e90a0d0dff60f3f8bc0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9565af3b3b774e90a0d0dff60f3f8bc0
record_format	dspace
spelling	oai:doaj.org-article:9565af3b3b774e90a0d0dff60f3f8bc02021-12-02T20:10:59ZA bio-inspired bistable recurrent cell allows for long-lasting memory.1932-620310.1371/journal.pone.0252676https://doaj.org/article/9565af3b3b774e90a0d0dff60f3f8bc02021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0252676https://doaj.org/toc/1932-6203Recurrent neural networks (RNNs) provide state-of-the-art performances in a wide variety of tasks that require memory. These performances can often be achieved thanks to gated recurrent cells such as gated recurrent units (GRU) and long short-term memory (LSTM). Standard gated cells share a layer internal state to store information at the network level, and long term memory is shaped by network-wide recurrent connection weights. Biological neurons on the other hand are capable of holding information at the cellular level for an arbitrary long amount of time through a process called bistability. Through bistability, cells can stabilize to different stable states depending on their own past state and inputs, which permits the durable storing of past information in neuron state. In this work, we take inspiration from biological neuron bistability to embed RNNs with long-lasting memory at the cellular level. This leads to the introduction of a new bistable biologically-inspired recurrent cell that is shown to strongly improves RNN performance on time-series which require very long memory, despite using only cellular connections (all recurrent connections are from neurons to themselves, i.e. a neuron state is not influenced by the state of other neurons). Furthermore, equipping this cell with recurrent neuromodulation permits to link them to standard GRU cells, taking a step towards the biological plausibility of GRU. With this link, this work paves the way for studying more complex and biologically plausible neuromodulation schemes as gating mechanisms in RNNs.Nicolas VecovenDamien ErnstGuillaume DrionPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 6, p e0252676 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Nicolas Vecoven Damien Ernst Guillaume Drion A bio-inspired bistable recurrent cell allows for long-lasting memory.
description	Recurrent neural networks (RNNs) provide state-of-the-art performances in a wide variety of tasks that require memory. These performances can often be achieved thanks to gated recurrent cells such as gated recurrent units (GRU) and long short-term memory (LSTM). Standard gated cells share a layer internal state to store information at the network level, and long term memory is shaped by network-wide recurrent connection weights. Biological neurons on the other hand are capable of holding information at the cellular level for an arbitrary long amount of time through a process called bistability. Through bistability, cells can stabilize to different stable states depending on their own past state and inputs, which permits the durable storing of past information in neuron state. In this work, we take inspiration from biological neuron bistability to embed RNNs with long-lasting memory at the cellular level. This leads to the introduction of a new bistable biologically-inspired recurrent cell that is shown to strongly improves RNN performance on time-series which require very long memory, despite using only cellular connections (all recurrent connections are from neurons to themselves, i.e. a neuron state is not influenced by the state of other neurons). Furthermore, equipping this cell with recurrent neuromodulation permits to link them to standard GRU cells, taking a step towards the biological plausibility of GRU. With this link, this work paves the way for studying more complex and biologically plausible neuromodulation schemes as gating mechanisms in RNNs.
format	article
author	Nicolas Vecoven Damien Ernst Guillaume Drion
author_facet	Nicolas Vecoven Damien Ernst Guillaume Drion
author_sort	Nicolas Vecoven
title	A bio-inspired bistable recurrent cell allows for long-lasting memory.
title_short	A bio-inspired bistable recurrent cell allows for long-lasting memory.
title_full	A bio-inspired bistable recurrent cell allows for long-lasting memory.
title_fullStr	A bio-inspired bistable recurrent cell allows for long-lasting memory.
title_full_unstemmed	A bio-inspired bistable recurrent cell allows for long-lasting memory.
title_sort	bio-inspired bistable recurrent cell allows for long-lasting memory.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/9565af3b3b774e90a0d0dff60f3f8bc0
work_keys_str_mv	AT nicolasvecoven abioinspiredbistablerecurrentcellallowsforlonglastingmemory AT damienernst abioinspiredbistablerecurrentcellallowsforlonglastingmemory AT guillaumedrion abioinspiredbistablerecurrentcellallowsforlonglastingmemory AT nicolasvecoven bioinspiredbistablerecurrentcellallowsforlonglastingmemory AT damienernst bioinspiredbistablerecurrentcellallowsforlonglastingmemory AT guillaumedrion bioinspiredbistablerecurrentcellallowsforlonglastingmemory
_version_	1718374961202069504

A bio-inspired bistable recurrent cell allows for long-lasting memory.

Ejemplares similares