Cargando…
MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks
Spiking Neural Networks (SNNs) are considered more biologically realistic and power-efficient as they imitate the fundamental mechanism of the human brain. Backpropagation (BP) based SNN learning algorithms that utilize deep learning frameworks have achieved good performance. However, those BP-based...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9531034/ https://www.ncbi.nlm.nih.gov/pubmed/36203801 http://dx.doi.org/10.3389/fnins.2022.945037 |
_version_ | 1784801817071190016 |
---|---|
author | Yu, Chengting Du, Yangkai Chen, Mufeng Wang, Aili Wang, Gaoang Li, Erping |
author_facet | Yu, Chengting Du, Yangkai Chen, Mufeng Wang, Aili Wang, Gaoang Li, Erping |
author_sort | Yu, Chengting |
collection | PubMed |
description | Spiking Neural Networks (SNNs) are considered more biologically realistic and power-efficient as they imitate the fundamental mechanism of the human brain. Backpropagation (BP) based SNN learning algorithms that utilize deep learning frameworks have achieved good performance. However, those BP-based algorithms partially ignore bio-interpretability. In modeling spike activity for biological plausible BP-based SNNs, we examine three properties: multiplicity, adaptability, and plasticity (MAP). Regarding multiplicity, we propose a Multiple-Spike Pattern (MSP) with multiple-spike transmission to improve model robustness in discrete time iterations. To realize adaptability, we adopt Spike Frequency Adaption (SFA) under MSP to reduce spike activities for enhanced efficiency. For plasticity, we propose a trainable state-free synapse that models spike response current to increase the diversity of spiking neurons for temporal feature extraction. The proposed SNN model achieves competitive performances on the N-MNIST and SHD neuromorphic datasets. In addition, experimental results demonstrate that the proposed three aspects are significant to iterative robustness, spike efficiency, and the capacity to extract spikes' temporal features. In summary, this study presents a realistic approach for bio-inspired spike activity with MAP, presenting a novel neuromorphic perspective for incorporating biological properties into spiking neural networks. |
format | Online Article Text |
id | pubmed-9531034 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-95310342022-10-05 MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks Yu, Chengting Du, Yangkai Chen, Mufeng Wang, Aili Wang, Gaoang Li, Erping Front Neurosci Neuroscience Spiking Neural Networks (SNNs) are considered more biologically realistic and power-efficient as they imitate the fundamental mechanism of the human brain. Backpropagation (BP) based SNN learning algorithms that utilize deep learning frameworks have achieved good performance. However, those BP-based algorithms partially ignore bio-interpretability. In modeling spike activity for biological plausible BP-based SNNs, we examine three properties: multiplicity, adaptability, and plasticity (MAP). Regarding multiplicity, we propose a Multiple-Spike Pattern (MSP) with multiple-spike transmission to improve model robustness in discrete time iterations. To realize adaptability, we adopt Spike Frequency Adaption (SFA) under MSP to reduce spike activities for enhanced efficiency. For plasticity, we propose a trainable state-free synapse that models spike response current to increase the diversity of spiking neurons for temporal feature extraction. The proposed SNN model achieves competitive performances on the N-MNIST and SHD neuromorphic datasets. In addition, experimental results demonstrate that the proposed three aspects are significant to iterative robustness, spike efficiency, and the capacity to extract spikes' temporal features. In summary, this study presents a realistic approach for bio-inspired spike activity with MAP, presenting a novel neuromorphic perspective for incorporating biological properties into spiking neural networks. Frontiers Media S.A. 2022-09-20 /pmc/articles/PMC9531034/ /pubmed/36203801 http://dx.doi.org/10.3389/fnins.2022.945037 Text en Copyright © 2022 Yu, Du, Chen, Wang, Wang and Li. https://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 Yu, Chengting Du, Yangkai Chen, Mufeng Wang, Aili Wang, Gaoang Li, Erping MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks |
title | MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks |
title_full | MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks |
title_fullStr | MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks |
title_full_unstemmed | MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks |
title_short | MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks |
title_sort | map-snn: mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9531034/ https://www.ncbi.nlm.nih.gov/pubmed/36203801 http://dx.doi.org/10.3389/fnins.2022.945037 |
work_keys_str_mv | AT yuchengting mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT duyangkai mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT chenmufeng mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT wangaili mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT wanggaoang mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT lierping mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks |