activity
20162026
most citedAdaptive Learning Rate via Covariance Matrix Based Preconditioning for Deep Neural Networks

10 citations · 22 across the 14 of their papers we have counts for

collaborators
Showing 2019 · stat.MLShow all

1 paper · 2 filters

stat.ML2019

Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks

Sekitoshi Kanai, Yasutoshi Ida, Yasuhiro Fujiwara +2

We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, rece…