20 citations · 44 across the 6 of their papers we have counts for
6 papers
Smoothness Analysis of Adversarial Training
Sekitoshi Kanai, Masanori Yamada, Hiroshi Takahashi +2
Deep neural networks are vulnerable to adversarial attacks. Recent studies about adversarial robustness focus on the loss landscape in the parameter space since it is related to op…
Adversarial Training Makes Weight Loss Landscape Sharper in Logistic Regression
Masanori Yamada, Sekitoshi Kanai, Tomoharu Iwata +4
Adversarial training is actively studied for learning robust models against adversarial examples. A recent study finds that adversarially trained models degenerate generalization p…
Supervised Anomaly Detection based on Deep Autoregressive Density Estimators
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. Density estimators have been w…
Autoencoding Binary Classifiers for Supervised Anomaly Detection
Yuki Yamanaka, Tomoharu Iwata, Hiroshi Takahashi +2
We propose the Autoencoding Binary Classifiers (ABC), a novel supervised anomaly detector based on the Autoencoder (AE). There are two main approaches in anomaly detection: supervi…
Variational Autoencoder with Implicit Optimal Priors
Hiroshi Takahashi, Tomoharu Iwata, Yuki Yamanaka +2
The variational autoencoder (VAE) is a powerful generative model that can estimate the probability of a data point by using latent variables. In the VAE, the posterior of the laten…
Sigsoftmax: Reanalysis of the Softmax Bottleneck
Sekitoshi Kanai, Yasuhiro Fujiwara, Yuki Yamanaka +1
Softmax is an output activation function for modeling categorical probability distributions in many applications of deep learning. However, a recent study revealed that softmax can…