1 citations · 2 across the 4 of their papers we have counts for
4 papers
Forecasting Japanese elections: A nonlinear machine-learning approach
Sota Kato, Xuan Luo, Budrul Ahsan +2
Despite Japan being one of the world's largest advanced democracies, the development of election forecasting models for its national elections remains limited. This study introduce…
Testing the Power-Law Hypothesis of the Inter-Conflict Interval
Hiroshi Okamoto, Iku Yoshimoto, Sota Kato +2
The severity of war, measured by battle deaths, follows a power-law distribution. Here, we demonstrate that power law also holds in the temporal aspects of interstate conflicts. A…
Out-of-Distribution Detection with Reconstruction Error and Typicality-based Penalty
Genki Osada, Takahashi Tsubasa, Budrul Ahsan +1
The task of out-of-distribution (OOD) detection is vital to realize safe and reliable operation for real-world applications. After the failure of likelihood-based detection in high…
Regularization with Latent Space Virtual Adversarial Training
Genki Osada, Budrul Ahsan, Revoti Prasad Bora +1
Virtual Adversarial Training (VAT) has shown impressive results among recently developed regularization methods called consistency regularization. VAT utilizes adversarial samples,…