Oscillatory Neural Networks for Edge AI Computing

Corentin Delacour; Stefania Carapezzi; Madeleine Abernot; Gabriele Boschetto; Nadine Azemard; Jérémie Salles; Thierry Gil; Aida Todri-Sanial

Conference papers

Oscillatory Neural Networks for Edge AI Computing

Corentin Delacour ¹ Stefania Carapezzi ¹ Madeleine Abernot ¹ Gabriele Boschetto ¹ Nadine Azemard ¹ Jérémie Salles ² Thierry Gil ² Aida Todri-Sanial ¹

1 SmartIES - Smart Integrated Electronic Systems

LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier

2 LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier

Abstract : In this paper, we showcase the innovative concept of implementing Oscillatory Neural Networks (ONNs) for neuromorphic computing with beyond CMOS devices based on vanadium dioxide to mimic neurons and resistors to emulate synapses. We explore ONN technology potentials from device to analog circuit-level simulations. We report that ONN behaves like an associative memory and can implement energy-based models such as Hopfield Neural Networks on edge devices. Finally, as a proof of concept, a reconfigurable digital ONN is implemented on FPGA for pattern recognition tasks.

Keywords : Oscillatory neural networks (ONN) Internet of- Things (IoT) edge artificial intelligence (edge AI) analog computing neuromorphic computing beyond-CMOS devices technology computer-aided design (TCAD) compact modeling circuit simulation

Document type :

Conference papers

Domain :

Engineering Sciences [physics] / Electronics

Complete list of metadata

https://hal-lirmm.ccsd.cnrs.fr/lirmm-03229257
Contributor : Corentin Delacour <>
Submitted on : Tuesday, May 18, 2021 - 6:52:05 PM
Last modification on : Wednesday, September 15, 2021 - 12:12:03 PM

Oscillatory Neural Networks for Edge AI Computing

Identifiers

Collections

Citation

Export

Metrics

75

Oscillatory Neural Networks for Edge AI Computing

Identifiers

Collections

Citation

Export

Share

Metrics

75