Multilayer magnetic skyrmion devices for spiking neural networks
Spintronic devices -based on magnetic solitons, such as the domain wall motion and the skyrmions, have shown a significant potential for applications in energy-efficient data storage and beyond CMOS computing architectures. Based on the magnetic multilayer hetero-structures, we propose a magnetic sk...
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/adad0e |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832542930874662912 |
|---|---|
| author | Aijaz H Lone Daniel N Rahimi Hossein Fariborzi Gianluca Setti |
| author_facet | Aijaz H Lone Daniel N Rahimi Hossein Fariborzi Gianluca Setti |
| author_sort | Aijaz H Lone |
| collection | DOAJ |
| description | Spintronic devices -based on magnetic solitons, such as the domain wall motion and the skyrmions, have shown a significant potential for applications in energy-efficient data storage and beyond CMOS computing architectures. Based on the magnetic multilayer hetero-structures, we propose a magnetic skyrmion-magnetic tunnel junction device structure, mimicking leaky integrate and fire LIF neuron characteristics. The device is controlled by spin-orbit torque-SOT driven skyrmion motion in the ferromagnetic thin film. The modified leaky integrate and fire LIF neuron-like characteristics are shown using the combination of SOT and the skyrmion position dependence of the demagnetization energy. The device characteristics are modeled as the modified LIF neuron. The LIF neuron is one of the fundamental spiking neuron models; we integrate the model in the three-layer spiking neural network (SNN) and convolutional CSNN framework to test these spiking neuron models to classify the MNIST and FMNIST datasets. In both architectures, the network achieves classification accuracy above 97.10%. Additionally, the LIF neuron latency is in ns; thus, when integrated with the CMOS, the proposed device structures and associated systems exhibit an excellent future for energy-efficient neuromorphic computing. |
| format | Article |
| id | doaj-art-ec7ed7a7060645b39ea5b96825dc5517 |
| 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-ec7ed7a7060645b39ea5b96825dc55172025-02-03T12:44:59ZengIOP PublishingNeuromorphic Computing and Engineering2634-43862025-01-015101400510.1088/2634-4386/adad0eMultilayer magnetic skyrmion devices for spiking neural networksAijaz H Lone0https://orcid.org/0000-0002-1687-2917Daniel N Rahimi1https://orcid.org/0009-0009-7869-1116Hossein Fariborzi2Gianluca Setti3Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST) , Thuwal 23955, Saudi ArabiaComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST) , Thuwal 23955, Saudi ArabiaComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST) , Thuwal 23955, Saudi ArabiaComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST) , Thuwal 23955, Saudi ArabiaSpintronic devices -based on magnetic solitons, such as the domain wall motion and the skyrmions, have shown a significant potential for applications in energy-efficient data storage and beyond CMOS computing architectures. Based on the magnetic multilayer hetero-structures, we propose a magnetic skyrmion-magnetic tunnel junction device structure, mimicking leaky integrate and fire LIF neuron characteristics. The device is controlled by spin-orbit torque-SOT driven skyrmion motion in the ferromagnetic thin film. The modified leaky integrate and fire LIF neuron-like characteristics are shown using the combination of SOT and the skyrmion position dependence of the demagnetization energy. The device characteristics are modeled as the modified LIF neuron. The LIF neuron is one of the fundamental spiking neuron models; we integrate the model in the three-layer spiking neural network (SNN) and convolutional CSNN framework to test these spiking neuron models to classify the MNIST and FMNIST datasets. In both architectures, the network achieves classification accuracy above 97.10%. Additionally, the LIF neuron latency is in ns; thus, when integrated with the CMOS, the proposed device structures and associated systems exhibit an excellent future for energy-efficient neuromorphic computing.https://doi.org/10.1088/2634-4386/adad0espintronicsskyrmionsLIF neuronsneuromorphic computingspiking neural network |
| spellingShingle | Aijaz H Lone Daniel N Rahimi Hossein Fariborzi Gianluca Setti Multilayer magnetic skyrmion devices for spiking neural networks Neuromorphic Computing and Engineering spintronics skyrmions LIF neurons neuromorphic computing spiking neural network |
| title | Multilayer magnetic skyrmion devices for spiking neural networks |
| title_full | Multilayer magnetic skyrmion devices for spiking neural networks |
| title_fullStr | Multilayer magnetic skyrmion devices for spiking neural networks |
| title_full_unstemmed | Multilayer magnetic skyrmion devices for spiking neural networks |
| title_short | Multilayer magnetic skyrmion devices for spiking neural networks |
| title_sort | multilayer magnetic skyrmion devices for spiking neural networks |
| topic | spintronics skyrmions LIF neurons neuromorphic computing spiking neural network |
| url | https://doi.org/10.1088/2634-4386/adad0e |
| work_keys_str_mv | AT aijazhlone multilayermagneticskyrmiondevicesforspikingneuralnetworks AT danielnrahimi multilayermagneticskyrmiondevicesforspikingneuralnetworks AT hosseinfariborzi multilayermagneticskyrmiondevicesforspikingneuralnetworks AT gianlucasetti multilayermagneticskyrmiondevicesforspikingneuralnetworks |