1 citations · 1 across the 3 of their papers we have counts for
6 papers
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…
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…
Energy-aware networked control systems under temporal logic specifications
Kazumune Hashimoto, Shuichi Adachi, Dimos V. Dimarogonas
In recent years, event and self-triggered control have been proposed as energy-aware control strategies to expand the life-time of battery powered devices in Networked Control Syst…
Aperiodic Sampled-Data Control via Explicit Transmission Mapping: A Set Invariance Approach
Kazumune Hashimoto, Dimos V. Dimarogonas, Shuichi Adachi
Event-triggered and self-triggered control have been proposed in recent years as promising control strategies to reduce communication resources in Networked Control Systems (NCSs).…
Event-Triggered Intermittent Sampling for Nonlinear Model Predictive Control
Kazumune Hashimoto, Shuichi Adachi, Dimos V. Dimarogonas
In this paper, we propose a new aperiodic formulation of model predictive control for nonlinear continuous-time systems. Unlike earlier approaches, we provide event-triggered condi…
Self-triggered control for constrained systems: a contractive set-based approach (Technical report)
Kazumune Hashimoto, Shuichi Adachi, Dimos V. Dimarogonas
In this paper, a self-triggered control scheme for constrained discrete-time control systems is presented. The key idea of our approach is to construct a transition system or a gra…