Tomoaki Shikina
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Tomoaki Shikina has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Daichi Teruya
Department of Computer and Information Sciences, Tokyo University of Agriculture and Technology, Tokyo 184-8588, Japan
1 shared publication - Hironori Nakajo
Tokyo University of Agriculture and Technology
1 shared publication - Huy-Dung Han
Department of Biomedical Engineering University of California Irvine 92697 Irvine CA USA
1 shared publication - Quoc-Dinh Nguyen
Department of Electronics and Telecommunication, Hanoi University of Science and Technology, Hanoi 10000, Vietnam
1 shared publication - Seiji Hotta
Tokyo University of Agriculture and Technology
1 shared publication
Latest Publications
- Open Access
- 22 November 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (22) , 11040
Leveraging Expert Knowledge for Label Noise Mitigation in Machine Learning
In training-based Machine Learning applications, the training data are frequently labeled by non-experts and expose substantial label noise which greatly alters the training models. In this work, a novel method for reducing the effect of label noise is introduced. The rules are created from expert knowledge to identify the incorrect non-expert training data. Using the gradient descent algorithm, the violating data samples are weighted less to mitigate their effects during model training. The proposed method is applied to the image classification problem using Manga109 and CIFAR-10 dataset. The experiments show that when the noise level is up to 50% our proposed method significantly increases the accuracy of the model compared to conventional learning methods.
- 22 November 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (22) , 11040
Open AccessLeveraging Expert Knowledge for Label Noise Mitigation in Machine Learning
In training-based Machine Learning applications, the training data are frequently labeled by non-experts and expose substantial label noise which greatly alters the training models. In this work, a novel method for reducing the effect of label noise is introduced. The rules are created from expert knowledge to identify the incorrect non-expert training data. Using the gradient descent algorithm, the violating data samples are weighted less to mitigate their effects during model training. The proposed method is applied to the image classification problem using Manga109 and CIFAR-10 dataset. The experiments show that when the noise level is up to 50% our proposed method significantly increases the accuracy of the model compared to conventional learning methods.