Domain Wall Magnetic Tunnel Junction Reliable Integrate and Fire Neuron
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913359929016320 |
|---|---|
| author | Cui1, Can Liu, Sam Kwon, Jaesuk Incorvia, Jean Anne C. |
| author_facet | Cui1, Can Liu, Sam Kwon, Jaesuk Incorvia, Jean Anne C. |
| contents | In spiking neural networks, neuron dynamics are described by the biologically realistic integrate-and-fire model that captures membrane potential accumulation and above-threshold firing behaviors. Among the hardware implementations of integrate-and-fire neuron devices, one important feature, reset, has been largely ignored. Here, we present the design and fabrication of a magnetic domain wall and magnetic tunnel junction based artificial integrate-and-fire neuron device that achieves reliable reset at the end of the integrate-fire cycle. We demonstrate the domain propagation in the domain wall racetrack (integration), reading using a magnetic tunnel junction (fire), and reset as the domain is ejected from the racetrack, showing the artificial neuron can be operated continuously over 100 integrate-fire-reset cycles. Both pulse amplitude and pulse number encoding is demonstrated. The device data is applied on an image classification task using a spiking neural network and shown to have comparable performance to an ideal leaky, integrate-and-fire neural network. These results achieve the first demonstration of reliable integrate-fire-reset in domain wall-magnetic tunnel junction-based neuron devices and shows the promise of spintronics for neuromorphic computing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14851 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Domain Wall Magnetic Tunnel Junction Reliable Integrate and Fire Neuron Cui1, Can Liu, Sam Kwon, Jaesuk Incorvia, Jean Anne C. Neural and Evolutionary Computing Mesoscale and Nanoscale Physics In spiking neural networks, neuron dynamics are described by the biologically realistic integrate-and-fire model that captures membrane potential accumulation and above-threshold firing behaviors. Among the hardware implementations of integrate-and-fire neuron devices, one important feature, reset, has been largely ignored. Here, we present the design and fabrication of a magnetic domain wall and magnetic tunnel junction based artificial integrate-and-fire neuron device that achieves reliable reset at the end of the integrate-fire cycle. We demonstrate the domain propagation in the domain wall racetrack (integration), reading using a magnetic tunnel junction (fire), and reset as the domain is ejected from the racetrack, showing the artificial neuron can be operated continuously over 100 integrate-fire-reset cycles. Both pulse amplitude and pulse number encoding is demonstrated. The device data is applied on an image classification task using a spiking neural network and shown to have comparable performance to an ideal leaky, integrate-and-fire neural network. These results achieve the first demonstration of reliable integrate-fire-reset in domain wall-magnetic tunnel junction-based neuron devices and shows the promise of spintronics for neuromorphic computing. |
| title | Domain Wall Magnetic Tunnel Junction Reliable Integrate and Fire Neuron |
| topic | Neural and Evolutionary Computing Mesoscale and Nanoscale Physics |
| url | https://arxiv.org/abs/2405.14851 |