Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware

Ever-growing demand for artificial intelligence has motivated research on unconventional computation based on physical devices. While such computation devices mimic brain-inspired analog information processing, the learning procedures still rely on methods optimized for digital processing such as ba...

Descripción completa

Detalles Bibliográficos
Autores principales: Nakajima, Mitsumasa, Inoue, Katsuma, Tanaka, Kenji, Kuniyoshi, Yasuo, Hashimoto, Toshikazu, Nakajima, Kohei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9792515/
https://www.ncbi.nlm.nih.gov/pubmed/36572696
http://dx.doi.org/10.1038/s41467-022-35216-2

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9792515/
https://www.ncbi.nlm.nih.gov/pubmed/36572696
http://dx.doi.org/10.1038/s41467-022-35216-2

Ejemplares similares