1 code implementation • 16 Feb 2024 • Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
In this study, we provide a theoretical framework for understanding learning from perturbations using a one-hidden-layer network trained on mutually orthogonal samples.
1 code implementation • 3 Feb 2024 • Koyu Mizutani, Haruki Mitarai, Kakeru Miyazaki, Soichiro Kumano, Toshihiko Yamasaki
Furthermore, the proposed model can predict even abnormal seismic intensity distributions, a task at conventional GMPEs often struggle.
no code implementations • 6 Sep 2022 • Koki Mukai, Soichiro Kumano, Toshihiko Yamasaki
In order to improve the robustness against out-of-distribution data, we present a frequency-based data augmentation technique that replaces the frequency components with other images of the same class.
no code implementations • 16 Aug 2022 • Koyu Mizutani, Haruki Mitarai, Kakeru Miyazaki, Ryugo Shimamura, Soichiro Kumano, Toshihiko Yamasaki
The ground motion prediction equation is commonly used to predict the seismic intensity distribution.
no code implementations • 29 May 2022 • Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Adversarial attacks have only focused on changing the predictions of the classifier, but their danger greatly depends on how the class is mistaken.
1 code implementation • 7 Dec 2020 • Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
In this paper, we address the question of whether there can be fooling images with no characteristic pattern of natural objects locally or globally.