Biological learning curves outperform existing ones in artificial intelligence algorithms

Recently, deep learning algorithms have outperformed human experts in various tasks across several domains; however, their characteristics are distant from current knowledge of neuroscience. The simulation results of biological learning algorithms presented herein outperform state-of-the-art optimal...

Descripción completa

Detalles Bibliográficos
Autores principales: Uzan, Herut, Sardi, Shira, Goldental, Amir, Vardi, Roni, Kanter, Ido
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2019
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6688986/
https://www.ncbi.nlm.nih.gov/pubmed/31399614
http://dx.doi.org/10.1038/s41598-019-48016-4

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6688986/
https://www.ncbi.nlm.nih.gov/pubmed/31399614
http://dx.doi.org/10.1038/s41598-019-48016-4

Ejemplares similares