Universal activation function for machine learning

This article proposes a universal activation function (UAF) that achieves near optimal performance in quantification, classification, and reinforcement learning (RL) problems. For any given problem, the gradient descent algorithms are able to evolve the UAF to a suitable activation function by tunin...

Descripción completa

Detalles Bibliográficos
Autores principales: Yuen, Brosnan, Hoang, Minh Tu, Dong, Xiaodai, Lu, Tao
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/PMC8455573/
https://www.ncbi.nlm.nih.gov/pubmed/34548504
http://dx.doi.org/10.1038/s41598-021-96723-8

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8455573/
https://www.ncbi.nlm.nih.gov/pubmed/34548504
http://dx.doi.org/10.1038/s41598-021-96723-8

Ejemplares similares