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

Saved in:
Bibliographic details
Volume: 9
Main Author: Sawada, Yoshihide
Sato, Yoshikuni
Nakada, Toru
Yamaguchi, Shunta
Ujimoto, Kei
Hayashi, Nobuhiro
Format: Journal Article
Language: English
Place of publication: BASEL MDPI 01.01.2019
MDPI AG
published in: Applied sciences Vol. 9; no. 1; pp. 128 - 140
ORCID: 0000-0002-9950-094X
0000-0001-7267-8660
Data of publication: 2019-01-01
ISSN: 2076-3417
2076-3417
EISSN: 2076-3417
Discipline: Engineering
Chemistry
Sciences (General)
Physics
Subjects:
Online Access: Fulltext
Database: Web of Science - Science Citation Index Expanded - 2019
Web of Knowledge
Science Citation Index Expanded
Web of Science
CrossRef
Directory of Open Access Journals
Database information Databases - DBIS