Cargando…

On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs

Neuromorphic computing is emerging to be a disruptive computational paradigm that attempts to emulate various facets of the underlying structure and functionalities of the brain in the algorithm and hardware design of next-generation machine learning platforms. This work goes beyond the focus of cur...

Descripción completa

Detalles Bibliográficos
Autores principales: Rastogi, Mehul, Lu, Sen, Islam, Nafiul, Sengupta, Abhronil
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7841294/
https://www.ncbi.nlm.nih.gov/pubmed/33519358
http://dx.doi.org/10.3389/fnins.2020.603796
_version_ 1783643774787780608
author Rastogi, Mehul
Lu, Sen
Islam, Nafiul
Sengupta, Abhronil
author_facet Rastogi, Mehul
Lu, Sen
Islam, Nafiul
Sengupta, Abhronil
author_sort Rastogi, Mehul
collection PubMed
description Neuromorphic computing is emerging to be a disruptive computational paradigm that attempts to emulate various facets of the underlying structure and functionalities of the brain in the algorithm and hardware design of next-generation machine learning platforms. This work goes beyond the focus of current neuromorphic computing architectures on computational models for neuron and synapse to examine other computational units of the biological brain that might contribute to cognition and especially self-repair. We draw inspiration and insights from computational neuroscience regarding functionalities of glial cells and explore their role in the fault-tolerant capacity of Spiking Neural Networks (SNNs) trained in an unsupervised fashion using Spike-Timing Dependent Plasticity (STDP). We characterize the degree of self-repair that can be enabled in such networks with varying degree of faults ranging from 50 to 90% and evaluate our proposal on the MNIST and Fashion-MNIST datasets.
format Online
Article
Text
id pubmed-7841294
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-78412942021-01-29 On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs Rastogi, Mehul Lu, Sen Islam, Nafiul Sengupta, Abhronil Front Neurosci Neuroscience Neuromorphic computing is emerging to be a disruptive computational paradigm that attempts to emulate various facets of the underlying structure and functionalities of the brain in the algorithm and hardware design of next-generation machine learning platforms. This work goes beyond the focus of current neuromorphic computing architectures on computational models for neuron and synapse to examine other computational units of the biological brain that might contribute to cognition and especially self-repair. We draw inspiration and insights from computational neuroscience regarding functionalities of glial cells and explore their role in the fault-tolerant capacity of Spiking Neural Networks (SNNs) trained in an unsupervised fashion using Spike-Timing Dependent Plasticity (STDP). We characterize the degree of self-repair that can be enabled in such networks with varying degree of faults ranging from 50 to 90% and evaluate our proposal on the MNIST and Fashion-MNIST datasets. Frontiers Media S.A. 2021-01-14 /pmc/articles/PMC7841294/ /pubmed/33519358 http://dx.doi.org/10.3389/fnins.2020.603796 Text en Copyright © 2021 Rastogi, Lu, Islam and Sengupta. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Rastogi, Mehul
Lu, Sen
Islam, Nafiul
Sengupta, Abhronil
On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs
title On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs
title_full On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs
title_fullStr On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs
title_full_unstemmed On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs
title_short On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs
title_sort on the self-repair role of astrocytes in stdp enabled unsupervised snns
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7841294/
https://www.ncbi.nlm.nih.gov/pubmed/33519358
http://dx.doi.org/10.3389/fnins.2020.603796
work_keys_str_mv AT rastogimehul ontheselfrepairroleofastrocytesinstdpenabledunsupervisedsnns
AT lusen ontheselfrepairroleofastrocytesinstdpenabledunsupervisedsnns
AT islamnafiul ontheselfrepairroleofastrocytesinstdpenabledunsupervisedsnns
AT senguptaabhronil ontheselfrepairroleofastrocytesinstdpenabledunsupervisedsnns