| Training robust neural networks using Lipschitz bounds P Pauli, A Koch, J Berberich, P Kohler, F Allgöwer IEEE Control Systems Letters 6, 121-126, 2021 | 205 | 2021 |
| Robust and optimal predictive control of the COVID-19 outbreak J Köhler, L Schwenkel, A Koch, J Berberich, P Pauli, F Allgöwer Annual Reviews in Control 51, 525-539, 2021 | 184 | 2021 |
| Offset-free setpoint tracking using neural network controllers P Pauli, J Köhler, J Berberich, A Koch, F Allgöwer Learning for dynamics and control, 992-1003, 2021 | 27 | 2021 |
| Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multipliers P Pauli, D Gramlich, J Berberich, F Allgöwer 2021 60th IEEE Conference on Decision and Control (CDC), 3611-3618, 2021 | 25 | 2021 |
| Sharing economy and optimal investment decisions for distributed solar generation R Henriquez-Auba, P Hidalgo-Gonzalez, P Pauli, D Kalathil, DS Callaway, ... Applied Energy 294, 117029, 2021 | 23 | 2021 |
| Neural network training under semidefinite constraints P Pauli, N Funcke, D Gramlich, MA Msalmi, F Allgöwer 2022 IEEE 61st Conference on Decision and Control (CDC), 2731-2736, 2022 | 22 | 2022 |
| Lipschitz constant estimation for 1d convolutional neural networks P Pauli, D Gramlich, F Allgöwer Learning for Dynamics and Control Conference, 1321-1332, 2023 | 18 | 2023 |
| Smartphone apps for learning progress and course revision P Pauli, A Koch, F Allgöwer IFAC-PapersOnLine 53 (2), 17368-17373, 2020 | 17 | 2020 |
| The sharing economy for residential solar generation R Henriquez-Auba, P Pauli, D Kalathil, DS Callaway, K Poolla 2018 IEEE Conference on Decision and Control (CDC), 7322-7329, 2018 | 15 | 2018 |
| Bounding the difference between model predictive control and neural networks R Drummond, S Duncan, M Turner, P Pauli, F Allgower Learning for Dynamics and Control Conference, 817-829, 2022 | 11 | 2022 |
| Convolutional neural networks as 2-D systems D Gramlich, P Pauli, CW Scherer, F Allgöwer, C Ebenbauer arXiv preprint arXiv:2303.03042, 2023 | 10 | 2023 |
| Facilitating learning progress in a first control course via Matlab apps A Koch, M Lorenzen, P Pauli, F Allgöwer IFAC-PapersOnLine 53 (2), 17356-17361, 2020 | 10 | 2020 |
| Lipschitz-bounded 1D convolutional neural networks using the Cayley transform and the controllability Gramian P Pauli, R Wang, IR Manchester, F Allgöwer 2023 62nd IEEE Conference on Decision and Control (CDC), 5345-5350, 2023 | 7 | 2023 |
| Novel quadratic constraints for extending LipSDP beyond slope-restricted activations P Pauli, A Havens, A Araujo, S Garg, F Khorrami, F Allgöwer, B Hu arXiv preprint arXiv:2401.14033, 2024 | 5 | 2024 |
| Robustness analysis and training of recurrent neural networks using dissipativity theory P Pauli, J Berberich, F Allgöwer at-Automatisierungstechnik 70 (8), 730-739, 2022 | 5 | 2022 |
| Learning soft constrained MPC value functions: Efficient MPC design and implementation providing stability and safety guarantees N Chatzikiriakos, KP Wabersich, F Berkel, P Pauli, A Iannelli 6th Annual Learning for Dynamics & Control Conference, 387-398, 2024 | 2 | 2024 |
| Lipschitz constant estimation for general neural network architectures using control tools P Pauli, D Gramlich, F Allgöwer arXiv preprint arXiv:2405.01125, 2024 | 2 | 2024 |
| Optimal delay assignment in delay-aware control of cyber-physical systems: A machine learning approach P Pauli, SM Dibaji, AM Annaswamy, A Chakrabortty 2019 IEEE 58th Conference on Decision and Control (CDC), 4583-4588, 2019 | 2 | 2019 |
| LipKernel: Lipschitz-Bounded Convolutional Neural Networks via Dissipative Layers P Pauli, R Wang, I Manchester, F Allgöwer arXiv preprint arXiv:2410.22258, 2024 | 1 | 2024 |
| State space representations of the Roesser type for convolutional layers P Pauli, D Gramlich, F Allgöwer IFAC-PapersOnLine 58 (17), 344-349, 2024 | 1 | 2024 |
Frank AllgöwerUniversity of Stuttgart, Universität StuttgartPreverjeni e-poštni naslov na ist.uni-stuttgart.de
