Deep Neural Networks with Multistate Activation Functions

We propose multistate activation functions (MSAFs) for deep neural networks (DNNs). These MSAFs are new kinds of activation functions which are capable of representing more than two states, including the N-order MSAFs and the symmetrical MSAF. DNNs with these MSAFs can be trained via conventional St...

Descripción completa

Detalles Bibliográficos
Autores principales: Cai, Chenghao, Xu, Yanyan, Ke, Dengfeng, Su, Kaile
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2015
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4581500/
https://www.ncbi.nlm.nih.gov/pubmed/26448739
http://dx.doi.org/10.1155/2015/721367

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4581500/
https://www.ncbi.nlm.nih.gov/pubmed/26448739
http://dx.doi.org/10.1155/2015/721367

Ejemplares similares