Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification

Abstract In the biological neural network, the learning process is achieved through massively parallel synaptic connections between neurons that can be adjusted in an analog manner. Recent developments in emerging synaptic devices and their networks can emulate the functionality of a biological neur...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sungho Kim, Bongsik Choi, Jinsu Yoon, Yongwoo Lee, Hee-Dong Kim, Min-Ho Kang, Sung-Jin Choi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2019
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/1293c3d3dff445459076ec2c8a20057c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1293c3d3dff445459076ec2c8a20057c
record_format	dspace
spelling	oai:doaj.org-article:1293c3d3dff445459076ec2c8a20057c2021-12-02T15:09:37ZBinarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification10.1038/s41598-019-48048-w2045-2322https://doaj.org/article/1293c3d3dff445459076ec2c8a20057c2019-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-019-48048-whttps://doaj.org/toc/2045-2322Abstract In the biological neural network, the learning process is achieved through massively parallel synaptic connections between neurons that can be adjusted in an analog manner. Recent developments in emerging synaptic devices and their networks can emulate the functionality of a biological neural network, which will be the fundamental building block for a neuromorphic computing architecture. However, on-chip implementation of a large-scale artificial neural network is still very challenging due to unreliable analog weight modulation in current synaptic device technology. Here, we demonstrate a binarized neural network (BNN) based on a gate-all-around silicon nanosheet synaptic transistor, where reliable digital-type weight modulation can contribute to improve the sustainability of the entire network. BNN is applied to three proof-of-concept examples: (1) handwritten digit classification (MNIST dataset), (2) face image classification (Yale dataset), and (3) experimental 3 × 3 binary pattern classifications using an integrated synaptic transistor network (total 9 × 9 × 2 162 cells) through a supervised online training procedure. The results consolidate the feasibility of binarized neural networks and pave the way toward building a reliable and large-scale artificial neural network by using more advanced conventional digital device technologies.Sungho KimBongsik ChoiJinsu YoonYongwoo LeeHee-Dong KimMin-Ho KangSung-Jin ChoiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 9, Iss 1, Pp 1-7 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Sungho Kim Bongsik Choi Jinsu Yoon Yongwoo Lee Hee-Dong Kim Min-Ho Kang Sung-Jin Choi Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification
description	Abstract In the biological neural network, the learning process is achieved through massively parallel synaptic connections between neurons that can be adjusted in an analog manner. Recent developments in emerging synaptic devices and their networks can emulate the functionality of a biological neural network, which will be the fundamental building block for a neuromorphic computing architecture. However, on-chip implementation of a large-scale artificial neural network is still very challenging due to unreliable analog weight modulation in current synaptic device technology. Here, we demonstrate a binarized neural network (BNN) based on a gate-all-around silicon nanosheet synaptic transistor, where reliable digital-type weight modulation can contribute to improve the sustainability of the entire network. BNN is applied to three proof-of-concept examples: (1) handwritten digit classification (MNIST dataset), (2) face image classification (Yale dataset), and (3) experimental 3 × 3 binary pattern classifications using an integrated synaptic transistor network (total 9 × 9 × 2 162 cells) through a supervised online training procedure. The results consolidate the feasibility of binarized neural networks and pave the way toward building a reliable and large-scale artificial neural network by using more advanced conventional digital device technologies.
format	article
author	Sungho Kim Bongsik Choi Jinsu Yoon Yongwoo Lee Hee-Dong Kim Min-Ho Kang Sung-Jin Choi
author_facet	Sungho Kim Bongsik Choi Jinsu Yoon Yongwoo Lee Hee-Dong Kim Min-Ho Kang Sung-Jin Choi
author_sort	Sungho Kim
title	Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification
title_short	Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification
title_full	Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification
title_fullStr	Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification
title_full_unstemmed	Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification
title_sort	binarized neural network with silicon nanosheet synaptic transistors for supervised pattern classification
publisher	Nature Portfolio
publishDate	2019
url	https://doaj.org/article/1293c3d3dff445459076ec2c8a20057c
work_keys_str_mv	AT sunghokim binarizedneuralnetworkwithsiliconnanosheetsynaptictransistorsforsupervisedpatternclassification AT bongsikchoi binarizedneuralnetworkwithsiliconnanosheetsynaptictransistorsforsupervisedpatternclassification AT jinsuyoon binarizedneuralnetworkwithsiliconnanosheetsynaptictransistorsforsupervisedpatternclassification AT yongwoolee binarizedneuralnetworkwithsiliconnanosheetsynaptictransistorsforsupervisedpatternclassification AT heedongkim binarizedneuralnetworkwithsiliconnanosheetsynaptictransistorsforsupervisedpatternclassification AT minhokang binarizedneuralnetworkwithsiliconnanosheetsynaptictransistorsforsupervisedpatternclassification AT sungjinchoi binarizedneuralnetworkwithsiliconnanosheetsynaptictransistorsforsupervisedpatternclassification
_version_	1718387797381873664

Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification

Ejemplares similares