Low-Rank Deep Convolutional Neural Network for Multitask Learning

In this paper, we propose a novel multitask learning method based on the deep convolutional network. The proposed deep network has four convolutional layers, three max-pooling layers, and two parallel fully connected layers. To adjust the deep network to multitask learning problem, we propose to lea...

Descripción completa

Detalles Bibliográficos
Autores principales: Su, Fang, Shang, Hai-Yang, Wang, Jing-Yan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6545796/
https://www.ncbi.nlm.nih.gov/pubmed/31236107
http://dx.doi.org/10.1155/2019/7410701