Cargando…
Impact of Synaptic Device Variations on Classification Accuracy in a Binarized Neural Network
Brain-inspired neuromorphic systems (hardware neural networks) are expected to be an energy-efficient computing architecture for solving cognitive tasks, which critically depend on the development of reliable synaptic weight storage (i.e., synaptic device). Although various nanoelectronic devices ha...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6811618/ https://www.ncbi.nlm.nih.gov/pubmed/31645636 http://dx.doi.org/10.1038/s41598-019-51814-5 |
_version_ | 1783462503125090304 |
---|---|
author | Kim, Sungho Kim, Hee-Dong Choi, Sung-Jin |
author_facet | Kim, Sungho Kim, Hee-Dong Choi, Sung-Jin |
author_sort | Kim, Sungho |
collection | PubMed |
description | Brain-inspired neuromorphic systems (hardware neural networks) are expected to be an energy-efficient computing architecture for solving cognitive tasks, which critically depend on the development of reliable synaptic weight storage (i.e., synaptic device). Although various nanoelectronic devices have successfully reproduced the learning rules of biological synapses through their internal analog conductance states, the sustainability of such devices is still in doubt due to the variability common to all nanoelectronic devices. Alternatively, a neuromorphic system based on a relatively more reliable digital-type switching device has been recently demonstrated, i.e., a binarized neural network (BNN). The synaptic device is a more mature digital-type switching device, and the training/recognition algorithm developed for the BNN enables the task of facial image classification with a supervised training scheme. Here, we quantitatively investigate the effects of device parameter variations on the classification accuracy; the parameters include the number of weight states (N(state)), the weight update margin (ΔG), and the weight update variation (G(var)). This analysis demonstrates the feasibility of the BNN and introduces a practical neuromorphic system based on mature, conventional digital device technologies. |
format | Online Article Text |
id | pubmed-6811618 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-68116182019-10-25 Impact of Synaptic Device Variations on Classification Accuracy in a Binarized Neural Network Kim, Sungho Kim, Hee-Dong Choi, Sung-Jin Sci Rep Article Brain-inspired neuromorphic systems (hardware neural networks) are expected to be an energy-efficient computing architecture for solving cognitive tasks, which critically depend on the development of reliable synaptic weight storage (i.e., synaptic device). Although various nanoelectronic devices have successfully reproduced the learning rules of biological synapses through their internal analog conductance states, the sustainability of such devices is still in doubt due to the variability common to all nanoelectronic devices. Alternatively, a neuromorphic system based on a relatively more reliable digital-type switching device has been recently demonstrated, i.e., a binarized neural network (BNN). The synaptic device is a more mature digital-type switching device, and the training/recognition algorithm developed for the BNN enables the task of facial image classification with a supervised training scheme. Here, we quantitatively investigate the effects of device parameter variations on the classification accuracy; the parameters include the number of weight states (N(state)), the weight update margin (ΔG), and the weight update variation (G(var)). This analysis demonstrates the feasibility of the BNN and introduces a practical neuromorphic system based on mature, conventional digital device technologies. Nature Publishing Group UK 2019-10-23 /pmc/articles/PMC6811618/ /pubmed/31645636 http://dx.doi.org/10.1038/s41598-019-51814-5 Text en © The Author(s) 2019 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/. |
spellingShingle | Article Kim, Sungho Kim, Hee-Dong Choi, Sung-Jin Impact of Synaptic Device Variations on Classification Accuracy in a Binarized Neural Network |
title | Impact of Synaptic Device Variations on Classification Accuracy in a Binarized Neural Network |
title_full | Impact of Synaptic Device Variations on Classification Accuracy in a Binarized Neural Network |
title_fullStr | Impact of Synaptic Device Variations on Classification Accuracy in a Binarized Neural Network |
title_full_unstemmed | Impact of Synaptic Device Variations on Classification Accuracy in a Binarized Neural Network |
title_short | Impact of Synaptic Device Variations on Classification Accuracy in a Binarized Neural Network |
title_sort | impact of synaptic device variations on classification accuracy in a binarized neural network |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6811618/ https://www.ncbi.nlm.nih.gov/pubmed/31645636 http://dx.doi.org/10.1038/s41598-019-51814-5 |
work_keys_str_mv | AT kimsungho impactofsynapticdevicevariationsonclassificationaccuracyinabinarizedneuralnetwork AT kimheedong impactofsynapticdevicevariationsonclassificationaccuracyinabinarizedneuralnetwork AT choisungjin impactofsynapticdevicevariationsonclassificationaccuracyinabinarizedneuralnetwork |