Cargando…
Trainable hardware for dynamical computing using error backpropagation through physical media
Neural networks are currently implemented on digital Von Neumann machines, which do not fully leverage their intrinsic parallelism. We demonstrate how to use a novel class of reconfigurable dynamical systems for analogue information processing, mitigating this problem. Our generic hardware platform...
| Autores principales: | , , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Nature Pub. Group
2015
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4382991/ https://www.ncbi.nlm.nih.gov/pubmed/25801303 http://dx.doi.org/10.1038/ncomms7729 |