Deep supervised learning with mixture of neural networks.

Deep Neural Network (DNN), as a deep architectures, has shown excellent performance in classification tasks. However, when the data has different distributions or contains some latent non-observed factors, it is difficult for DNN to train a single model to perform well on the classification tasks. I...

Full description

Bibliographic Details
Published in:Artificial Intelligence in Medicine Vol. 102
Main Authors: Hu, Yaxian, Luo, Senlin, Han, Longfei, Pan, Limin, Zhang, Tiemei
Format: equations & formulas research tables/charts Journal Article
Published: Elsevier B.V. Jan2020
Online Access:View this record in EBSCOhost