Multi-Scale Modeling and Simulation Flow for Oscillatory Neural Networks for Edge Computing

Stefania Carapezzi; Corentin Delacour; Gabriele Boschetto; Elisabetta Corti; Madeleine Abernot; Ahmed Nejim; Thierry Gil; Siegfried Karg; Aida Todri-Sanial

doi:10.1109/NEWCAS50681.2021.9462761

Multi-Scale Modeling and Simulation Flow for Oscillatory Neural Networks for Edge Computing

Stefania Carapezzi
, Corentin Delacour
, Gabriele Boschetto
, Elisabetta Corti
, Madeleine Abernot
, Ahmed Nejim
, Thierry Gil
, Siegfried Karg
, Aida Todri-Sanial

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

7 Citations (Scopus)

Abstract

An oscillatory neural network (ONN) is a neuromorphic computing paradigm based on encoding of information into the phases of oscillators. In this paper we present an ONN whose elemental unit, the "neuron", is implemented through a beyond-CMOS device based on vanadium dioxide (VO 2 ). Such ONN technology provides ultra-low power solutions for performing pattern recognition tasks, and it is ideally suited for edge computing applications. However, exploring the groundwork of the beyond-CMOS ONN paradigm is mandatory premise for its industry-level exploitation. Such foundation entails the building of a holistic simulation flow from materials and devices to circuits, to allow assessment of ONN performance. In this work we report results of this advanced designing approach with special focus over the VO 2 oscillator. This establishes the ground to scale up to evaluate beyond-CMOS ONN functionalities for pattern recognition.

Original language	English
Title of host publication	2021 19th IEEE International New Circuits and Systems Conference (NEWCAS)
Publisher	Institute of Electrical and Electronics Engineers
Number of pages	5
ISBN (Electronic)	978-1-6654-2429-5
DOIs	https://doi.org/10.1109/NEWCAS50681.2021.9462761
Publication status	Published - 25 Jun 2021
Externally published	Yes
Event	19th IEEE International New Circuits and Systems Conference (NEWCAS 2021) - Toulon, France Duration: 13 Jun 2021 → 16 Jun 2021

Conference

Conference	19th IEEE International New Circuits and Systems Conference (NEWCAS 2021)
Country/Territory	France
City	Toulon
Period	13/06/21 → 16/06/21

Keywords

Oscillatory neural networks (ONN)
density functional theory (DFT)
technology computer aided design (TCAD)
circuit simulation
Internet-of-Things (IoT)
edge artificial intelligence (edge AI)
neuromorphic computing

Access to Document

10.1109/NEWCAS50681.2021.9462761

Cite this

Carapezzi, S., Delacour, C., Boschetto, G., Corti, E., Abernot, M., Nejim, A., Gil, T., Karg, S., & Todri-Sanial, A. (2021). Multi-Scale Modeling and Simulation Flow for Oscillatory Neural Networks for Edge Computing. In 2021 19th IEEE International New Circuits and Systems Conference (NEWCAS) Article 9462761 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/NEWCAS50681.2021.9462761

@inproceedings{399ebff345e148d093735bb8ce62c404,

title = "Multi-Scale Modeling and Simulation Flow for Oscillatory Neural Networks for Edge Computing",

abstract = "An oscillatory neural network (ONN) is a neuromorphic computing paradigm based on encoding of information into the phases of oscillators. In this paper we present an ONN whose elemental unit, the {"}neuron{"}, is implemented through a beyond-CMOS device based on vanadium dioxide (VO 2 ). Such ONN technology provides ultra-low power solutions for performing pattern recognition tasks, and it is ideally suited for edge computing applications. However, exploring the groundwork of the beyond-CMOS ONN paradigm is mandatory premise for its industry-level exploitation. Such foundation entails the building of a holistic simulation flow from materials and devices to circuits, to allow assessment of ONN performance. In this work we report results of this advanced designing approach with special focus over the VO 2 oscillator. This establishes the ground to scale up to evaluate beyond-CMOS ONN functionalities for pattern recognition.",

keywords = "Oscillatory neural networks (ONN), density functional theory (DFT), technology computer aided design (TCAD), circuit simulation, Internet-of-Things (IoT), edge artificial intelligence (edge AI), neuromorphic computing",

author = "Stefania Carapezzi and Corentin Delacour and Gabriele Boschetto and Elisabetta Corti and Madeleine Abernot and Ahmed Nejim and Thierry Gil and Siegfried Karg and Aida Todri-Sanial",

year = "2021",

month = jun,

day = "25",

doi = "10.1109/NEWCAS50681.2021.9462761",

language = "English",

booktitle = "2021 19th IEEE International New Circuits and Systems Conference (NEWCAS)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "19th IEEE International New Circuits and Systems Conference (NEWCAS 2021) ; Conference date: 13-06-2021 Through 16-06-2021",

}

Carapezzi, S, Delacour, C, Boschetto, G, Corti, E, Abernot, M, Nejim, A, Gil, T, Karg, S & Todri-Sanial, A 2021, Multi-Scale Modeling and Simulation Flow for Oscillatory Neural Networks for Edge Computing. in 2021 19th IEEE International New Circuits and Systems Conference (NEWCAS)., 9462761, Institute of Electrical and Electronics Engineers, 19th IEEE International New Circuits and Systems Conference (NEWCAS 2021), Toulon, France, 13/06/21. https://doi.org/10.1109/NEWCAS50681.2021.9462761

Multi-Scale Modeling and Simulation Flow for Oscillatory Neural Networks for Edge Computing. / Carapezzi, Stefania; Delacour, Corentin; Boschetto, Gabriele et al.
2021 19th IEEE International New Circuits and Systems Conference (NEWCAS). Institute of Electrical and Electronics Engineers, 2021. 9462761.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Multi-Scale Modeling and Simulation Flow for Oscillatory Neural Networks for Edge Computing

AU - Carapezzi, Stefania

AU - Delacour, Corentin

AU - Boschetto, Gabriele

AU - Corti, Elisabetta

AU - Abernot, Madeleine

AU - Nejim, Ahmed

AU - Gil, Thierry

AU - Karg, Siegfried

AU - Todri-Sanial, Aida

PY - 2021/6/25

Y1 - 2021/6/25

N2 - An oscillatory neural network (ONN) is a neuromorphic computing paradigm based on encoding of information into the phases of oscillators. In this paper we present an ONN whose elemental unit, the "neuron", is implemented through a beyond-CMOS device based on vanadium dioxide (VO 2 ). Such ONN technology provides ultra-low power solutions for performing pattern recognition tasks, and it is ideally suited for edge computing applications. However, exploring the groundwork of the beyond-CMOS ONN paradigm is mandatory premise for its industry-level exploitation. Such foundation entails the building of a holistic simulation flow from materials and devices to circuits, to allow assessment of ONN performance. In this work we report results of this advanced designing approach with special focus over the VO 2 oscillator. This establishes the ground to scale up to evaluate beyond-CMOS ONN functionalities for pattern recognition.

AB - An oscillatory neural network (ONN) is a neuromorphic computing paradigm based on encoding of information into the phases of oscillators. In this paper we present an ONN whose elemental unit, the "neuron", is implemented through a beyond-CMOS device based on vanadium dioxide (VO 2 ). Such ONN technology provides ultra-low power solutions for performing pattern recognition tasks, and it is ideally suited for edge computing applications. However, exploring the groundwork of the beyond-CMOS ONN paradigm is mandatory premise for its industry-level exploitation. Such foundation entails the building of a holistic simulation flow from materials and devices to circuits, to allow assessment of ONN performance. In this work we report results of this advanced designing approach with special focus over the VO 2 oscillator. This establishes the ground to scale up to evaluate beyond-CMOS ONN functionalities for pattern recognition.

KW - Oscillatory neural networks (ONN)

KW - density functional theory (DFT)

KW - technology computer aided design (TCAD)

KW - circuit simulation

KW - Internet-of-Things (IoT)

KW - edge artificial intelligence (edge AI)

KW - neuromorphic computing

UR - https://www.scopus.com/pages/publications/85114637234

U2 - 10.1109/NEWCAS50681.2021.9462761

DO - 10.1109/NEWCAS50681.2021.9462761

M3 - Conference contribution

BT - 2021 19th IEEE International New Circuits and Systems Conference (NEWCAS)

PB - Institute of Electrical and Electronics Engineers

T2 - 19th IEEE International New Circuits and Systems Conference (NEWCAS 2021)

Y2 - 13 June 2021 through 16 June 2021

ER -

Multi-Scale Modeling and Simulation Flow for Oscillatory Neural Networks for Edge Computing

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this