Cargando…
Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks
Experimental studies support the notion of spike-based neuronal information processing in the brain, with neural circuits exhibiting a wide range of temporally-based coding strategies to rapidly and efficiently represent sensory stimuli. Accordingly, it would be desirable to apply spike-based comput...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8072060/ https://www.ncbi.nlm.nih.gov/pubmed/33912021 http://dx.doi.org/10.3389/fncom.2021.617862 |
_version_ | 1783683842547122176 |
---|---|
author | Gardner, Brian Grüning, André |
author_facet | Gardner, Brian Grüning, André |
author_sort | Gardner, Brian |
collection | PubMed |
description | Experimental studies support the notion of spike-based neuronal information processing in the brain, with neural circuits exhibiting a wide range of temporally-based coding strategies to rapidly and efficiently represent sensory stimuli. Accordingly, it would be desirable to apply spike-based computation to tackling real-world challenges, and in particular transferring such theory to neuromorphic systems for low-power embedded applications. Motivated by this, we propose a new supervised learning method that can train multilayer spiking neural networks to solve classification problems based on a rapid, first-to-spike decoding strategy. The proposed learning rule supports multiple spikes fired by stochastic hidden neurons, and yet is stable by relying on first-spike responses generated by a deterministic output layer. In addition to this, we also explore several distinct, spike-based encoding strategies in order to form compact representations of presented input data. We demonstrate the classification performance of the learning rule as applied to several benchmark datasets, including MNIST. The learning rule is capable of generalizing from the data, and is successful even when used with constrained network architectures containing few input and hidden layer neurons. Furthermore, we highlight a novel encoding strategy, termed “scanline encoding,” that can transform image data into compact spatiotemporal patterns for subsequent network processing. Designing constrained, but optimized, network structures and performing input dimensionality reduction has strong implications for neuromorphic applications. |
format | Online Article Text |
id | pubmed-8072060 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-80720602021-04-27 Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks Gardner, Brian Grüning, André Front Comput Neurosci Neuroscience Experimental studies support the notion of spike-based neuronal information processing in the brain, with neural circuits exhibiting a wide range of temporally-based coding strategies to rapidly and efficiently represent sensory stimuli. Accordingly, it would be desirable to apply spike-based computation to tackling real-world challenges, and in particular transferring such theory to neuromorphic systems for low-power embedded applications. Motivated by this, we propose a new supervised learning method that can train multilayer spiking neural networks to solve classification problems based on a rapid, first-to-spike decoding strategy. The proposed learning rule supports multiple spikes fired by stochastic hidden neurons, and yet is stable by relying on first-spike responses generated by a deterministic output layer. In addition to this, we also explore several distinct, spike-based encoding strategies in order to form compact representations of presented input data. We demonstrate the classification performance of the learning rule as applied to several benchmark datasets, including MNIST. The learning rule is capable of generalizing from the data, and is successful even when used with constrained network architectures containing few input and hidden layer neurons. Furthermore, we highlight a novel encoding strategy, termed “scanline encoding,” that can transform image data into compact spatiotemporal patterns for subsequent network processing. Designing constrained, but optimized, network structures and performing input dimensionality reduction has strong implications for neuromorphic applications. Frontiers Media S.A. 2021-04-12 /pmc/articles/PMC8072060/ /pubmed/33912021 http://dx.doi.org/10.3389/fncom.2021.617862 Text en Copyright © 2021 Gardner and Grüning. 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 Gardner, Brian Grüning, André Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks |
title | Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks |
title_full | Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks |
title_fullStr | Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks |
title_full_unstemmed | Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks |
title_short | Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks |
title_sort | supervised learning with first-to-spike decoding in multilayer spiking neural networks |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8072060/ https://www.ncbi.nlm.nih.gov/pubmed/33912021 http://dx.doi.org/10.3389/fncom.2021.617862 |
work_keys_str_mv | AT gardnerbrian supervisedlearningwithfirsttospikedecodinginmultilayerspikingneuralnetworks AT gruningandre supervisedlearningwithfirsttospikedecodinginmultilayerspikingneuralnetworks |