DBN Structure Design Algorithm for Different Datasets Based on Information Entropy and Reconstruction Error

Deep belief networks (DBNs) of deep learning technology have been successfully used in many fields. However, the structure of a DBN is difficult to design for different datasets. Hence, a DBN structure design algorithm based on information entropy and reconstruction error is proposed. Unlike previou...

Descripción completa

Detalles Bibliográficos
Autores principales: Jiang, Jianjun, Zhang, Jing, Zhang, Lijia, Ran, Xiaomin, Jiang, Jun, Wu, Yifan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7512514/
https://www.ncbi.nlm.nih.gov/pubmed/33266651
http://dx.doi.org/10.3390/e20120927

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7512514/
https://www.ncbi.nlm.nih.gov/pubmed/33266651
http://dx.doi.org/10.3390/e20120927

Ejemplares similares