Daniel Frank

Daniel Frank

System theory, Machine Learning

Publications

Regularised Neural Network-Based Nonlinear System Identification with Prior System Knowledge

International Journal of Control, 2026

We propose a regularisation approach for neural network-based nonlinear system identification that incorporates prior system knowledge.

Recommended citation: Frank, D., Holicki, T., Scherer, C. W., & Staab, S. (2026). "Regularised neural network-based nonlinear system identification with prior system knowledge." International Journal of Control. https://doi.org/10.1080/00207179.2026.2679228

Learning the Dynamics of Nonlinear Systems with Regional Stability Guarantees through Linear Matrix Inequality Constraints

Accepted at the IFAC World Congress 2026, Busan, South Korea (preprint on arXiv), 2026

We derive linear matrix inequality constraints on recurrent neural network parameters that certify regional stability guarantees for learned nonlinear system dynamics.

Recommended citation: Frank, D., Shakib, F., & Staab, S. (2026). "Learning the dynamics of nonlinear systems with regional stability guarantees through linear matrix inequality constraints." arXiv:2605.18292. Accepted at the IFAC World Congress 2026. https://arxiv.org/abs/2605.18292

Robust Recurrent Neural Network to Identify Ship Motion in Open Water with Performance Guarantees

Technical report, arXiv, 2022

We represent a recurrent neural network as a linear time-invariant system with nonlinear disturbances and introduce parameter constraints that guarantee finite gain stability, applied to learning ship motion in open water.

Recommended citation: Frank, D., Aspandi Latif, D., Muehlebach, M., Unger, B., & Staab, S. (2022). "Robust recurrent neural network to identify ship motion in open water with performance guarantees." Technical report, arXiv:2212.05781. https://arxiv.org/abs/2212.05781