Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science

Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural networks (e.g. sparsity, scale-freeness), we argue that (contrary to general prac...

Descripción completa

Detalles Bibliográficos
Autores principales: Mocanu, Decebal Constantin, Mocanu, Elena, Stone, Peter, Nguyen, Phuong H., Gibescu, Madeleine, Liotta, Antonio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2018
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6008460/
https://www.ncbi.nlm.nih.gov/pubmed/29921910
http://dx.doi.org/10.1038/s41467-018-04316-3

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6008460/
https://www.ncbi.nlm.nih.gov/pubmed/29921910
http://dx.doi.org/10.1038/s41467-018-04316-3

Ejemplares similares