SpinONN: energy efficient brain-inspired spintronics-based Hopfield oscillatory neural network for image denoising

This work proposes a Spintronics-based Hopfield oscillatory neural network (HONN) that leverages dynamic frequency-encoded electrical synchronization between two spin-torque vortex nano-oscillators (SVNOs) as oscillatory neurons, with a non-volatile memristor as a coupling element (synaptic connecti...

Full description

Saved in:
Bibliographic Details
Main Authors: Sandeep Soni, Yasser Rezaeiyan, Tim Boehnert, Hooman Farkhani, Ricardo Ferreira, Brajesh Kumar Kaushik, Farshad Moradi, Sonal Shreya
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Neuromorphic Computing and Engineering
Subjects:
Online Access:https://doi.org/10.1088/2634-4386/ade622
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417386673831936
author Sandeep Soni
Yasser Rezaeiyan
Tim Boehnert
Hooman Farkhani
Ricardo Ferreira
Brajesh Kumar Kaushik
Farshad Moradi
Sonal Shreya
author_facet Sandeep Soni
Yasser Rezaeiyan
Tim Boehnert
Hooman Farkhani
Ricardo Ferreira
Brajesh Kumar Kaushik
Farshad Moradi
Sonal Shreya
author_sort Sandeep Soni
collection DOAJ
description This work proposes a Spintronics-based Hopfield oscillatory neural network (HONN) that leverages dynamic frequency-encoded electrical synchronization between two spin-torque vortex nano-oscillators (SVNOs) as oscillatory neurons, with a non-volatile memristor as a coupling element (synaptic connection). The frequency synchronization mechanism, inspired by the brain’s oscillatory dynamics, enables the synchronization of SVNOs, facilitating efficient information processing of the dynamic oscillatory signals within the network. This coupling mechanism has been investigated to design SVNOs-based neural circuit design topology for enhanced frequency-encoded computing using SVNOs neurons and memristive coupling synapses. The proposed transmission gate-based SVNO oscillatory neural circuit has been implemented, offering efficient frequency synchronization, non-linearity, and a less complex neural circuit design. Further, a hybrid Spintronic/complementary metal oxide semiconductor 16-SVNOs HONN is designed, and circuit-based simulations are performed, which offer a promising solution for building robust and scalable HONNs. We achieve fast computation (∼4 ns) and offer significantly lower energy consumption (∼24 fJ/neuron) as compared to VO _2 -based ONN architectures (8× faster and 4× reduced power/neuron). Finally, we demonstrate an image denoising application on the proposed SVNO-based HONN hardware-compatible accelerator using an image-splitting approach with parallel processing. The 32 × 32 street view house number image dataset is efficiently split into blocks and processed through the 16-SVNOs HONN design, dividing the image into 4 × 4 blocks. Lastly, we examined the peak signal-to-noise ratio and structural similarity index measure for denoising the images with an efficient splitting approach for scalability. The network effectively denoises images while maintaining image quality, demonstrating the potential of the HONN hardware-compatible architecture for large-scale and real-time applications.
format Article
id doaj-art-7b19ce7bcddf4c9fbe8fa740cf394c8f
institution Kabale University
issn 2634-4386
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series Neuromorphic Computing and Engineering
spelling doaj-art-7b19ce7bcddf4c9fbe8fa740cf394c8f2025-08-20T03:32:51ZengIOP PublishingNeuromorphic Computing and Engineering2634-43862025-01-015303400110.1088/2634-4386/ade622SpinONN: energy efficient brain-inspired spintronics-based Hopfield oscillatory neural network for image denoisingSandeep Soni0https://orcid.org/0000-0003-3137-9124Yasser Rezaeiyan1Tim Boehnert2Hooman Farkhani3Ricardo Ferreira4Brajesh Kumar Kaushik5Farshad Moradi6Sonal Shreya7https://orcid.org/0000-0001-6340-0368Department of Electrical and Computer Engineering, Aarhus University , Aarhus, Aarhus N 8200, Denmark; Department of Electronics and Communication Engineering, Indian Institute of Technology , Roorkee, Uttarakhand, IndiaDepartment of Electrical and Computer Engineering, Aarhus University , Aarhus, Aarhus N 8200, DenmarkInternational Iberian Nanotechnology Laboratory (INL) , Braga, PortugalDepartment of Electrical and Computer Engineering, Aarhus University , Aarhus, Aarhus N 8200, DenmarkInternational Iberian Nanotechnology Laboratory (INL) , Braga, PortugalDepartment of Electronics and Communication Engineering, Indian Institute of Technology , Roorkee, Uttarakhand, IndiaDepartment of Electrical and Computer Engineering, Aarhus University , Aarhus, Aarhus N 8200, DenmarkDepartment of Electrical and Computer Engineering, Aarhus University , Aarhus, Aarhus N 8200, DenmarkThis work proposes a Spintronics-based Hopfield oscillatory neural network (HONN) that leverages dynamic frequency-encoded electrical synchronization between two spin-torque vortex nano-oscillators (SVNOs) as oscillatory neurons, with a non-volatile memristor as a coupling element (synaptic connection). The frequency synchronization mechanism, inspired by the brain’s oscillatory dynamics, enables the synchronization of SVNOs, facilitating efficient information processing of the dynamic oscillatory signals within the network. This coupling mechanism has been investigated to design SVNOs-based neural circuit design topology for enhanced frequency-encoded computing using SVNOs neurons and memristive coupling synapses. The proposed transmission gate-based SVNO oscillatory neural circuit has been implemented, offering efficient frequency synchronization, non-linearity, and a less complex neural circuit design. Further, a hybrid Spintronic/complementary metal oxide semiconductor 16-SVNOs HONN is designed, and circuit-based simulations are performed, which offer a promising solution for building robust and scalable HONNs. We achieve fast computation (∼4 ns) and offer significantly lower energy consumption (∼24 fJ/neuron) as compared to VO _2 -based ONN architectures (8× faster and 4× reduced power/neuron). Finally, we demonstrate an image denoising application on the proposed SVNO-based HONN hardware-compatible accelerator using an image-splitting approach with parallel processing. The 32 × 32 street view house number image dataset is efficiently split into blocks and processed through the 16-SVNOs HONN design, dividing the image into 4 × 4 blocks. Lastly, we examined the peak signal-to-noise ratio and structural similarity index measure for denoising the images with an efficient splitting approach for scalability. The network effectively denoises images while maintaining image quality, demonstrating the potential of the HONN hardware-compatible architecture for large-scale and real-time applications.https://doi.org/10.1088/2634-4386/ade622brain-inspired computingcoupled oscillatorHopfield neural network (HNN)image denoisingOscillatory neural network (ONN)Spin-torque vortex nano-oscillators (SVNO)
spellingShingle Sandeep Soni
Yasser Rezaeiyan
Tim Boehnert
Hooman Farkhani
Ricardo Ferreira
Brajesh Kumar Kaushik
Farshad Moradi
Sonal Shreya
SpinONN: energy efficient brain-inspired spintronics-based Hopfield oscillatory neural network for image denoising
Neuromorphic Computing and Engineering
brain-inspired computing
coupled oscillator
Hopfield neural network (HNN)
image denoising
Oscillatory neural network (ONN)
Spin-torque vortex nano-oscillators (SVNO)
title SpinONN: energy efficient brain-inspired spintronics-based Hopfield oscillatory neural network for image denoising
title_full SpinONN: energy efficient brain-inspired spintronics-based Hopfield oscillatory neural network for image denoising
title_fullStr SpinONN: energy efficient brain-inspired spintronics-based Hopfield oscillatory neural network for image denoising
title_full_unstemmed SpinONN: energy efficient brain-inspired spintronics-based Hopfield oscillatory neural network for image denoising
title_short SpinONN: energy efficient brain-inspired spintronics-based Hopfield oscillatory neural network for image denoising
title_sort spinonn energy efficient brain inspired spintronics based hopfield oscillatory neural network for image denoising
topic brain-inspired computing
coupled oscillator
Hopfield neural network (HNN)
image denoising
Oscillatory neural network (ONN)
Spin-torque vortex nano-oscillators (SVNO)
url https://doi.org/10.1088/2634-4386/ade622
work_keys_str_mv AT sandeepsoni spinonnenergyefficientbraininspiredspintronicsbasedhopfieldoscillatoryneuralnetworkforimagedenoising
AT yasserrezaeiyan spinonnenergyefficientbraininspiredspintronicsbasedhopfieldoscillatoryneuralnetworkforimagedenoising
AT timboehnert spinonnenergyefficientbraininspiredspintronicsbasedhopfieldoscillatoryneuralnetworkforimagedenoising
AT hoomanfarkhani spinonnenergyefficientbraininspiredspintronicsbasedhopfieldoscillatoryneuralnetworkforimagedenoising
AT ricardoferreira spinonnenergyefficientbraininspiredspintronicsbasedhopfieldoscillatoryneuralnetworkforimagedenoising
AT brajeshkumarkaushik spinonnenergyefficientbraininspiredspintronicsbasedhopfieldoscillatoryneuralnetworkforimagedenoising
AT farshadmoradi spinonnenergyefficientbraininspiredspintronicsbasedhopfieldoscillatoryneuralnetworkforimagedenoising
AT sonalshreya spinonnenergyefficientbraininspiredspintronicsbasedhopfieldoscillatoryneuralnetworkforimagedenoising