Next Article in Journal / Special Issue
Using the Guided Fireworks Algorithm for Local Backlight Dimming
Previous Article in Journal
Stability and Heat Input Controllability of Two Different Modulations for Double-Pulse MIG Welding
Previous Article in Special Issue
Accelerating Image Classification using Feature Map Similarity in Convolutional Neural Networks
Article

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

1
Technology Innovation Division, Panasonic Corporation, Tokyo 135-8072, Japan
2
Business Innovation Division, Panasonic Corporation, Osaka 570-8501, Japan
3
Department of Life Science and Technology, Tokyo Institute of Technology, Tokyo 152-8550, Japan
*
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(1), 128; https://doi.org/10.3390/app9010128
Received: 22 October 2018 / Revised: 29 November 2018 / Accepted: 26 December 2018 / Published: 1 January 2019
(This article belongs to the Special Issue Advanced Intelligent Imaging Technology)
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 can provide a solution to this problem. Previous methods regularize all layers, including the output layer, by estimating the relation vectors, which are then used instead of one-hot target vectors of the target domain. These vectors are estimated by averaging the target domain data of each target domain label in the output space. This method improves the classification performance, but it does not consider the relation between the relation vectors. From this point of view, we propose a relation vector modification based on constrained pairwise repulsive forces. High pairwise repulsive forces provide large distances between the relation vectors. In addition, the risk of divergence is mitigated by the constraint based on distributions of the output vectors of the target domain data. We apply our method to two simulation experiments and a disease classification using two-dimensional electrophoresis images. The experimental results show that reusing all layers through our estimation method is effective, especially for a significantly small number of the target domain data. View Full-Text
Keywords: deep neural network; transfer learning; proteomics; sepsis classification deep neural network; transfer learning; proteomics; sepsis classification
Show Figures

Graphical abstract

MDPI and ACS Style

Sawada, Y.; Sato, Y.; Nakada, T.; Yamaguchi, S.; Ujimoto, K.; Hayashi, N. Improvement in Classification Performance Based on Target Vector Modification for All-Transfer Deep Learning. Appl. Sci. 2019, 9, 128. https://doi.org/10.3390/app9010128

AMA Style

Sawada Y, Sato Y, Nakada T, Yamaguchi S, Ujimoto K, Hayashi N. Improvement in Classification Performance Based on Target Vector Modification for All-Transfer Deep Learning. Applied Sciences. 2019; 9(1):128. https://doi.org/10.3390/app9010128

Chicago/Turabian Style

Sawada, Yoshihide; Sato, Yoshikuni; Nakada, Toru; Yamaguchi, Shunta; Ujimoto, Kei; Hayashi, Nobuhiro. 2019. "Improvement in Classification Performance Based on Target Vector Modification for All-Transfer Deep Learning" Appl. Sci. 9, no. 1: 128. https://doi.org/10.3390/app9010128

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop