Cargando…

Highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons

A spiking neural network (SNN) is considered a high-performance learning system that matches the digital circuits and presents higher efficiency due to the architecture and computation of spiking neurons. While implementing a SNN on a field-programmable gate array (FPGA), the gradient back-propagati...

Descripción completa

Detalles Bibliográficos
Autores principales: Gao, Tian, Deng, Bin, Wang, Jiang, Yi, Guosheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9554099/
https://www.ncbi.nlm.nih.gov/pubmed/36248664
http://dx.doi.org/10.3389/fnins.2022.929644
_version_ 1784806618488111104
author Gao, Tian
Deng, Bin
Wang, Jiang
Yi, Guosheng
author_facet Gao, Tian
Deng, Bin
Wang, Jiang
Yi, Guosheng
author_sort Gao, Tian
collection PubMed
description A spiking neural network (SNN) is considered a high-performance learning system that matches the digital circuits and presents higher efficiency due to the architecture and computation of spiking neurons. While implementing a SNN on a field-programmable gate array (FPGA), the gradient back-propagation through layers consumes a surprising number of resources. In this paper, we aim to realize an efficient architecture of SNN on the FPGA to reduce resource and power consumption. The multi-compartment leaky integrate-and-fire (MLIF) model is used to convert spike trains to the plateau potential in dendrites. We accumulate the potential in the apical dendrite during the training period. The average of this accumulative result is the dendritic plateau potential and is used to guide the updates of synaptic weights. Based on this architecture, the SNN is implemented on FPGA efficiently. In the implementation of a neuromorphic learning system, the shift multiplier (shift MUL) module and piecewise linear (PWL) algorithm are used to replace multipliers and complex nonlinear functions to match the digital circuits. The neuromorphic learning system is constructed with resources on FPGA without dataflow between on-chip and off-chip memories. Our neuromorphic learning system performs with higher resource utilization and power efficiency than previous on-chip learning systems.
format Online
Article
Text
id pubmed-9554099
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-95540992022-10-13 Highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons Gao, Tian Deng, Bin Wang, Jiang Yi, Guosheng Front Neurosci Neuroscience A spiking neural network (SNN) is considered a high-performance learning system that matches the digital circuits and presents higher efficiency due to the architecture and computation of spiking neurons. While implementing a SNN on a field-programmable gate array (FPGA), the gradient back-propagation through layers consumes a surprising number of resources. In this paper, we aim to realize an efficient architecture of SNN on the FPGA to reduce resource and power consumption. The multi-compartment leaky integrate-and-fire (MLIF) model is used to convert spike trains to the plateau potential in dendrites. We accumulate the potential in the apical dendrite during the training period. The average of this accumulative result is the dendritic plateau potential and is used to guide the updates of synaptic weights. Based on this architecture, the SNN is implemented on FPGA efficiently. In the implementation of a neuromorphic learning system, the shift multiplier (shift MUL) module and piecewise linear (PWL) algorithm are used to replace multipliers and complex nonlinear functions to match the digital circuits. The neuromorphic learning system is constructed with resources on FPGA without dataflow between on-chip and off-chip memories. Our neuromorphic learning system performs with higher resource utilization and power efficiency than previous on-chip learning systems. Frontiers Media S.A. 2022-09-28 /pmc/articles/PMC9554099/ /pubmed/36248664 http://dx.doi.org/10.3389/fnins.2022.929644 Text en Copyright © 2022 Gao, Deng, Wang and Yi. 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
Gao, Tian
Deng, Bin
Wang, Jiang
Yi, Guosheng
Highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons
title Highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons
title_full Highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons
title_fullStr Highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons
title_full_unstemmed Highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons
title_short Highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons
title_sort highly efficient neuromorphic learning system of spiking neural network with multi-compartment leaky integrate-and-fire neurons
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9554099/
https://www.ncbi.nlm.nih.gov/pubmed/36248664
http://dx.doi.org/10.3389/fnins.2022.929644
work_keys_str_mv AT gaotian highlyefficientneuromorphiclearningsystemofspikingneuralnetworkwithmulticompartmentleakyintegrateandfireneurons
AT dengbin highlyefficientneuromorphiclearningsystemofspikingneuralnetworkwithmulticompartmentleakyintegrateandfireneurons
AT wangjiang highlyefficientneuromorphiclearningsystemofspikingneuralnetworkwithmulticompartmentleakyintegrateandfireneurons
AT yiguosheng highlyefficientneuromorphiclearningsystemofspikingneuralnetworkwithmulticompartmentleakyintegrateandfireneurons