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...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| 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 |