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...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-09-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.945037/full |
_version_ | 1811183572104511488 |
---|---|
author | Chengting Yu Chengting Yu Yangkai Du Mufeng Chen Aili Wang Aili Wang Gaoang Wang Erping Li Erping Li |
author_facet | Chengting Yu Chengting Yu Yangkai Du Mufeng Chen Aili Wang Aili Wang Gaoang Wang Erping Li Erping Li |
author_sort | Chengting Yu |
collection | DOAJ |
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. |
first_indexed | 2024-04-11T09:49:02Z |
format | Article |
id | doaj.art-cf7d67733f044808b5746e6868f7339f |
institution | Directory Open Access Journal |
issn | 1662-453X |
language | English |
last_indexed | 2024-04-11T09:49:02Z |
publishDate | 2022-09-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Neuroscience |
spelling | doaj.art-cf7d67733f044808b5746e6868f7339f2022-12-22T04:30:53ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-09-011610.3389/fnins.2022.945037945037MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networksChengting Yu0Chengting Yu1Yangkai Du2Mufeng Chen3Aili Wang4Aili Wang5Gaoang Wang6Erping Li7Erping Li8College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, ChinaZhejiang University - University of Illinois at Urbana-Champaign Institute, Zhejiang University, Haining, ChinaCollege of Computer Science and Technology, Zhejiang University, Hangzhou, ChinaCollege of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, ChinaCollege of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, ChinaZhejiang University - University of Illinois at Urbana-Champaign Institute, Zhejiang University, Haining, ChinaZhejiang University - University of Illinois at Urbana-Champaign Institute, Zhejiang University, Haining, ChinaCollege of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, ChinaZhejiang University - University of Illinois at Urbana-Champaign Institute, Zhejiang University, Haining, ChinaSpiking 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.https://www.frontiersin.org/articles/10.3389/fnins.2022.945037/fullspiking neural network (SNN)leaky integrate-and-fire (LIF) neuronmultiple spike pattern (MSP)spike frequency adaption (SFA)state-free synaptic response model (SFSRM)neuromorphic recognition |
spellingShingle | Chengting Yu Chengting Yu Yangkai Du Mufeng Chen Aili Wang Aili Wang Gaoang Wang Erping Li Erping Li MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks Frontiers in Neuroscience spiking neural network (SNN) leaky integrate-and-fire (LIF) neuron multiple spike pattern (MSP) spike frequency adaption (SFA) state-free synaptic response model (SFSRM) neuromorphic recognition |
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 | spiking neural network (SNN) leaky integrate-and-fire (LIF) neuron multiple spike pattern (MSP) spike frequency adaption (SFA) state-free synaptic response model (SFSRM) neuromorphic recognition |
url | https://www.frontiersin.org/articles/10.3389/fnins.2022.945037/full |
work_keys_str_mv | AT chengtingyu mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT chengtingyu mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT yangkaidu mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT mufengchen mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT ailiwang mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT ailiwang mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT gaoangwang mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT erpingli mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks AT erpingli mapsnnmappingspikeactivitieswithmultiplicityadaptabilityandplasticityintobioplausiblespikingneuralnetworks |