Cargando…
Transferable learning on analog hardware
While analog neural network (NN) accelerators promise massive energy and time savings, an important challenge is to make them robust to static fabrication error. Present-day training methods for programmable photonic interferometer circuits, a leading analog NN platform, do not produce networks that...
| Autores principales: | , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
American Association for the Advancement of Science
2023
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10337896/ https://www.ncbi.nlm.nih.gov/pubmed/37436989 http://dx.doi.org/10.1126/sciadv.adh3436 |