Training all-mechanical neural networks for task learning through in situ backpropagation
Abstract Recent advances unveiled physical neural networks as promising machine learning platforms, offering faster and more energy-efficient information processing. Compared with extensively-studied optical neural networks, the development of mechanical neural networks remains nascent and faces sig...
| Những tác giả chính: | , |
|---|---|
| Định dạng: | Bài viết |
| Ngôn ngữ: | English |
| Được phát hành: |
Nature Portfolio
2024-12-01
|
| Loạt: | Nature Communications |
| Truy cập trực tuyến: | https://doi.org/10.1038/s41467-024-54849-z |