Spontaneous sparse learning for PCM-based memristor neural networks

Neural networks trained by backpropagation have achieved tremendous successes on numerous intelligent tasks. However, naïve gradient-based training and updating methods on memristors impede applications due to intrinsic material properties. Here, we built a 39 nm 1 Gb phase change memory (PCM) memri...

Descripción completa

Detalles Bibliográficos
Autores principales: Lim, Dong-Hyeok, Wu, Shuang, Zhao, Rong, Lee, Jung-Hoon, Jeong, Hongsik, Shi, Luping
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7803975/
https://www.ncbi.nlm.nih.gov/pubmed/33436611
http://dx.doi.org/10.1038/s41467-020-20519-z

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7803975/
https://www.ncbi.nlm.nih.gov/pubmed/33436611
http://dx.doi.org/10.1038/s41467-020-20519-z

Ejemplares similares