Ebihara Lab Homepage

Study Topics

We explore analysis and synthesis of dynamical systems from broad perspective using mathematical systems theory. Currently, we are actively working on the reliability/stability verification of AI systems on the basis of optimization and control theory.

Special Events

News

July 2021: Conference Paper Accepted, New!!
The following paper has been accepted for presentation at IEEE Conference on Decision and Control 2021.
Y. Ebihara, H. Waki, V. Magron, N. H. A. Mai, D. Peaucelle, and S. Tarbouriech:
Stability Analysis of Recurrent Neural Networks by IQC with Copositive Mutipliers

June 2021: Journal Paper Accepted
The following paper, which has already been accepted for presentation at European Control Conference 2021 (ECC2021), has been selected as one of the very best papers at ECC2021 and accepted for publication at the 2021 ECC Special Issue of the European Journal of Control.
Y. Ebihara, H. Waki, V. Magron, N. H. A. Mai, D. Peaucelle, and S. Tarbouriech:
l2 Induced Norm Analysis of Discrete-Time LTI Systems for Nonnegative Input Signals and Its Application to Stability Analysis of Recurrent Neural Networks

April 2021: Conference Paper Accepted
The following paper has been accepted for presentation at European Control Conference 2021.
Y. Ebihara, H. Waki, V. Magron, N. H. A. Mai, D. Peaucelle, and S. Tarbouriech:
l2 Induced Norm Analysis of Discrete-Time LTI Systems for Nonnegative Input Signals and Its Application to Stability Analysis of Recurrent Neural Networks

April 2021: New Research Project Launched
JSPS KAKENHI 21H01354 (PI: Y. Ebihara)
"Stability Analysis and Optimal Synthesis of Recurrent Neural Networks by Conic Programming"
Collaborators: H. Waki (IMI, Kyushu University, Japan), D. Peaucelle, S. Tarbouriech, J. B. Lasserre, V. Magron, N. Mai (LAAS-CNRS, France).