no code implementations • 2 Mar 2021 • Sekitoshi Kanai, Masanori Yamada, Hiroshi Takahashi, Yuki Yamanaka, Yasutoshi Ida
We reveal that the constraint of adversarial attacks is one cause of the non-smoothness and that the smoothness depends on the types of the constraints.
no code implementations • 5 Feb 2021 • Masanori Yamada, Sekitoshi Kanai, Tomoharu Iwata, Tomokatsu Takahashi, Yuki Yamanaka, Hiroshi Takahashi, Atsutoshi Kumagai
We theoretically and experimentally confirm that the weight loss landscape becomes sharper as the magnitude of the noise of adversarial training increases in the linear logistic regression model.
no code implementations • 12 Apr 2019 • Tomoharu Iwata, Yuki Yamanaka
We propose a supervised anomaly detection method based on neural density estimators, where the negative log likelihood is used for the anomaly score.
no code implementations • 26 Mar 2019 • Yuki Yamanaka, Tomoharu Iwata, Hiroshi Takahashi, Masanori Yamada, Sekitoshi Kanai
Since our approach becomes able to reconstruct the normal data points accurately and fails to reconstruct the known and unknown anomalies, it can accurately discriminate both known and unknown anomalies from normal data points.
1 code implementation • 14 Sep 2018 • Hiroshi Takahashi, Tomoharu Iwata, Yuki Yamanaka, Masanori Yamada, Satoshi Yagi
However, KL divergence with the aggregated posterior cannot be calculated in a closed form, which prevents us from using this optimal prior.
no code implementations • NeurIPS 2018 • Sekitoshi Kanai, Yasuhiro Fujiwara, Yuki Yamanaka, Shuichi Adachi
On the basis of this analysis, we propose sigsoftmax, which is composed of a multiplication of an exponential function and sigmoid function.