%0 Conference Paper %1 Baier2023 %A Baier, Alexandra %A Aspandi, Decky %A Staab, Steffen %B Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23 %D 2023 %I International Joint Conferences on Artificial Intelligence Organization %K %T ReLiNet: Stable and Explainable Multistep Prediction with Recurrent Linear Parameter Varying Networks %X Multistep prediction models are essential for the simulation and model-predictive control of dynamical systems. Verifying the safety of such models is a multi-faceted problem requiring both system-theoretic guarantees as well as establishing trust with human users. In this work, we propose a novel approach, ReLiNet (Recurrent Linear Parameter Varying Network), to ensure safety for multistep prediction of dynamical systems. Our approach simplifies a recurrent neural network to a switched linear system that is constrained to guarantee exponential stability, which acts as a surrogate for safety from a system-theoretic perspective. Furthermore, ReLiNet’s computation can be reduced to a single linear model for each time step, resulting in predictions that are explainable by definition, thereby establishing trust from a human-centric perspective. Our quantitative experiments show that ReLiNet achieves prediction accuracy comparable to that of state-of-the-art recurrent neural networks, while achieving more faithful and robust explanations compared to the model-agnostic explanation method of LIME.

@inproceedings{Baier2023, abstract = {Multistep prediction models are essential for the simulation and model-predictive control of dynamical systems. Verifying the safety of such models is a multi-faceted problem requiring both system-theoretic guarantees as well as establishing trust with human users. In this work, we propose a novel approach, ReLiNet (Recurrent Linear Parameter Varying Network), to ensure safety for multistep prediction of dynamical systems. Our approach simplifies a recurrent neural network to a switched linear system that is constrained to guarantee exponential stability, which acts as a surrogate for safety from a system-theoretic perspective. Furthermore, ReLiNet’s computation can be reduced to a single linear model for each time step, resulting in predictions that are explainable by definition, thereby establishing trust from a human-centric perspective. Our quantitative experiments show that ReLiNet achieves prediction accuracy comparable to that of state-of-the-art recurrent neural networks, while achieving more faithful and robust explanations compared to the model-agnostic explanation method of LIME.}, added-at = {2024-01-12T14:46:07.000+0100}, author = {Baier, Alexandra and Aspandi, Decky and Staab, Steffen}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/258e3d8a67f20a1766353bcb2fdf910b1/totounan}, booktitle = {Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23}, interhash = {2e996c3803dd3030b150002c1cabf6a1}, intrahash = {58e3d8a67f20a1766353bcb2fdf910b1}, keywords = {}, month = aug, note = {Main Track}, publisher = {International Joint Conferences on Artificial Intelligence Organization}, timestamp = {2024-01-12T14:46:07.000+0100}, title = {ReLiNet: Stable and Explainable Multistep Prediction with Recurrent Linear Parameter Varying Networks}, year = 2023 }