Improvement in Classification Performance Based on Target Vector Modification for All-Transfer Deep Learning

Improvement in Classification Performance Based on Target Vector Modification for All-Transfer Deep Learning

This paper proposes a target vector modification method for the all-transfer deep learning (ATDL) method. Deep neural networks (DNNs) have been used widely in many applications; however, the DNN has been known to be problematic when large amounts of training data are not available. Transfer learning...

Full description

Bibliographic Details
Main Authors: Yoshihide Sawada, Yoshikuni Sato, Toru Nakada, Shunta Yamaguchi, Kei Ujimoto, Nobuhiro Hayashi
Format: Article
Language:English
Published: MDPI AG 2019-01-01
Series:Applied Sciences
Subjects:
deep neural network
transfer learning
proteomics
sepsis classification
Online Access:http://www.mdpi.com/2076-3417/9/1/128

Internet

http://www.mdpi.com/2076-3417/9/1/128

Similar Items