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

June 2024: Conference Paper Accepted New!!
The following paper that deals with the reliability verification of neural networks has been accepted for presentation at the SICE Festival 2024 with Annual Conference (SICE FES 2024).
T. Yuno, S. Nishinaka, R. Saeki, and Y. Ebihara,
Stability Analysis of Feedback Systems with Idempotent Nonlinearities via Static O'Shea-Zames-Falb Multipliers
June 2024: Conference Paper Accepted New!!
The following paper that deals with the reliability verification of neural networks has been accepted for presentation at The 4th IFAC Conference of Modelling, Identification and Control of Nonlinear Systems (MICNON2024).
S. Nishinaka, R. Saeki, T. Yuno, Y. Ebihara, V. Magron, D. Peaucelle, S. Zoboli, and S. Tarbouriech,
Stability Analysis of Feedback Systems with ReLU Nonlinearities via Semialgebraic Set Representation
May 2024: Journal Paper Accepted New!!
The following paper that deals with the reliability verification of neural networks has been accepted for publication at IEEE Control Systems Letters.
T. Yuno, K. Fukuchi, Y. Ebihara,
A Lyapunov-Based Method of Reducing Activation Functions of Recurrent Neural Networks for Stability Analysis
March 2024: Conference Paper Accepted New!!
The following paper that deals with the reliability verification of neural networks has been accepted for presentation at European Control Conference 2024.
Y. Ebihara, X. Dai, T. Yuno, V. Magron, D. Peaucelle, and S. Tarbouriech,
Local Lipschitz Constant Computation of ReLU-FNNs: Upper Bound Computation with Exactness Verification
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).