Realization and training of an inverter-based printed neuromorphic computing system

Abstract Emerging applications in soft robotics, wearables, smart consumer products or IoT-devices benefit from soft materials, flexible substrates in conjunction with electronic functionality. Due to high production costs and conformity restrictions, rigid silicon technologies do not meet applicati...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Dennis D. Weller, Michael Hefenbrock, Michael Beigl, Jasmin Aghassi-Hagmann, Mehdi B. Tahoori
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/1a496ee5200c4c7283f7bd188bf66b71
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1a496ee5200c4c7283f7bd188bf66b71
record_format	dspace
spelling	oai:doaj.org-article:1a496ee5200c4c7283f7bd188bf66b712021-12-02T15:38:11ZRealization and training of an inverter-based printed neuromorphic computing system10.1038/s41598-021-88396-02045-2322https://doaj.org/article/1a496ee5200c4c7283f7bd188bf66b712021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88396-0https://doaj.org/toc/2045-2322Abstract Emerging applications in soft robotics, wearables, smart consumer products or IoT-devices benefit from soft materials, flexible substrates in conjunction with electronic functionality. Due to high production costs and conformity restrictions, rigid silicon technologies do not meet application requirements in these new domains. However, whenever signal processing becomes too comprehensive, silicon technology must be used for the high-performance computing unit. At the same time, designing everything in flexible or printed electronics using conventional digital logic is not feasible yet due to the limitations of printed technologies in terms of performance, power and integration density. We propose to rather use the strengths of neuromorphic computing architectures consisting in their homogeneous topologies, few building blocks and analog signal processing to be mapped to an inkjet-printed hardware architecture. It has remained a challenge to demonstrate non-linear elements besides weighted aggregation. We demonstrate in this work printed hardware building blocks such as inverter-based comprehensive weight representation and resistive crossbars as well as printed transistor-based activation functions. In addition, we present a learning algorithm developed to train the proposed printed NCS architecture based on specific requirements and constraints of the technology.Dennis D. WellerMichael HefenbrockMichael BeiglJasmin Aghassi-HagmannMehdi B. TahooriNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Dennis D. Weller Michael Hefenbrock Michael Beigl Jasmin Aghassi-Hagmann Mehdi B. Tahoori Realization and training of an inverter-based printed neuromorphic computing system
description	Abstract Emerging applications in soft robotics, wearables, smart consumer products or IoT-devices benefit from soft materials, flexible substrates in conjunction with electronic functionality. Due to high production costs and conformity restrictions, rigid silicon technologies do not meet application requirements in these new domains. However, whenever signal processing becomes too comprehensive, silicon technology must be used for the high-performance computing unit. At the same time, designing everything in flexible or printed electronics using conventional digital logic is not feasible yet due to the limitations of printed technologies in terms of performance, power and integration density. We propose to rather use the strengths of neuromorphic computing architectures consisting in their homogeneous topologies, few building blocks and analog signal processing to be mapped to an inkjet-printed hardware architecture. It has remained a challenge to demonstrate non-linear elements besides weighted aggregation. We demonstrate in this work printed hardware building blocks such as inverter-based comprehensive weight representation and resistive crossbars as well as printed transistor-based activation functions. In addition, we present a learning algorithm developed to train the proposed printed NCS architecture based on specific requirements and constraints of the technology.
format	article
author	Dennis D. Weller Michael Hefenbrock Michael Beigl Jasmin Aghassi-Hagmann Mehdi B. Tahoori
author_facet	Dennis D. Weller Michael Hefenbrock Michael Beigl Jasmin Aghassi-Hagmann Mehdi B. Tahoori
author_sort	Dennis D. Weller
title	Realization and training of an inverter-based printed neuromorphic computing system
title_short	Realization and training of an inverter-based printed neuromorphic computing system
title_full	Realization and training of an inverter-based printed neuromorphic computing system
title_fullStr	Realization and training of an inverter-based printed neuromorphic computing system
title_full_unstemmed	Realization and training of an inverter-based printed neuromorphic computing system
title_sort	realization and training of an inverter-based printed neuromorphic computing system
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/1a496ee5200c4c7283f7bd188bf66b71
work_keys_str_mv	AT dennisdweller realizationandtrainingofaninverterbasedprintedneuromorphiccomputingsystem AT michaelhefenbrock realizationandtrainingofaninverterbasedprintedneuromorphiccomputingsystem AT michaelbeigl realizationandtrainingofaninverterbasedprintedneuromorphiccomputingsystem AT jasminaghassihagmann realizationandtrainingofaninverterbasedprintedneuromorphiccomputingsystem AT mehdibtahoori realizationandtrainingofaninverterbasedprintedneuromorphiccomputingsystem
_version_	1718386156677103616

Realization and training of an inverter-based printed neuromorphic computing system

Ejemplares similares