{"type":"ScholarlyArticle","title":"ReLiNet: Stable and Explainable Multistep Prediction with Recurrent Linear Parameter Varying Networks","authors":[{"name":"Alexandra Baier","slug":"alexandra-baier","given":"Alexandra","family":"Baier","affiliation":"Analytic Computing , University of Stuttgart , Germany"},{"name":"Decky Aspandi","slug":"decky-aspandi","given":"Decky","family":"Aspandi","affiliation":"Analytic Computing , University of Stuttgart , Germany"},{"name":"Steffen Staab","slug":"steffen-staab","given":"Steffen","family":"Staab","affiliation":"Analytic Computing , University of Stuttgart , Germany; Web and Internet Science Research Group , University of Southampton , Great Britain"}],"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.","doi":"10.24963/ijcai.2023/385","url":"https://ijcai.org/proceedings/2023/385","pdf":"https://ijcai.org/proceedings/2023/0385.pdf","markdown":"https://ijcai.org/proceedings/2023/385.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/385","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Machine Learning","track":"Main Track","number":385,"pages":{"first":3461,"last":3469},"keywords":["AI Ethics, Trust, Fairness: ETF: Explainability and interpretability","AI Ethics, Trust, Fairness: ETF: Safety and robustness","Machine Learning: ML: Recurrent networks"],"videos":[],"references":[{"position":1,"raw":"[Alvarez Melis and Jaakkola, 2018] David Alvarez Melis and Tommi Jaakkola. Towards robust interpretability with self-explaining neural networks. In NeurIPS, volume 31.","title":"Towards robust interpretability with self-explaining neural networks","authors":"Alvarez Melis, ; ] Jaakkola, Alvarez David, Tommi Melis, Jaakkola","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"Curran Associates, Inc., 2018.","title":null,"authors":"Curran Associates, Inc","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Baier and Frank, 2023] Alexandra Baier and Daniel Frank. deepsysid: System Identification Toolkit for Multistep Prediction using Deep Learning. https://doi.org/10.18419/ darus-3455, 2023. Accessed: 2023-05-24.","title":"deepsysid: System Identification Toolkit for Multistep Prediction using Deep Learning","authors":"Frank ; Baier, Alexandra Baier, Daniel Frank","year":"2023","venue":null,"doi":"10.18419/darus-3455","url":"https://doi.org/10.18419/darus-3455,2023","internal_url":null},{"position":4,"raw":"[Baier and Staab, 2022] Alexandra Baier and Steffen Staab. A Simulated 4-DOF Ship Motion Dataset for System Iden- tification under Environmental Disturbances. https://doi. org/10.18419/darus-2905, 2022. Accessed: 2023-05-24.","title":"A Simulated 4-DOF Ship Motion Dataset for System Identification under Environmental Disturbances","authors":"Alexandra Baier, Steffen Staab","year":"2023","venue":null,"doi":"10.18419/darus-2905","url":"https://doi.org/10.18419/darus-2905,2022","internal_url":null},{"position":5,"raw":"[Baier et al., 2023] Alexandra Baier, Decky Aspandi, and Steffen Staab. Supplements for \"ReLiNet: Stable and Explainable Multistep Prediction with Recurrent Linear Parameter Varying Networks\". https://doi.org/10.18419/ darus-3457, 2023. Accessed: 2023-05-24.","title":"Supplements for \"ReLiNet: Stable and Explainable Multistep Prediction with Recurrent Linear Parameter Varying Networks","authors":"Alexandra Baier, Decky Aspandi, Steffen Staab","year":"2023","venue":null,"doi":"10.18419/darus-3457","url":"https://doi.org/10.18419/darus-3457,2023","internal_url":null},{"position":6,"raw":"[Bamieh and Giarré, 2002] Bassam Bamieh and Laura Gi- arré. Identification of linear parameter varying models. Int. J. Robust and Nonlinear Control, 12(9):841-853, 2002.","title":"Identification of linear parameter varying models","authors":"Bassam Bamieh, Laura Giarré","year":"2002","venue":"Int. J. Robust and Nonlinear Control","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Bhatt et al., 2020] Umang Bhatt, Adrian Weller, and José M. F. Moura. Evaluating and aggregating feature-based model explanations. In IJCAI, pages 3016-3022, 7 2020.","title":"Evaluating and aggregating feature-based model explanations","authors":"Umang Bhatt, Adrian Weller, M F José, Moura","year":"2020","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/417"},{"position":8,"raw":"[Bohle et al., 2021] Moritz Bohle, Mario Fritz, and Bernt Schiele. Convolutional dynamic alignment networks for interpretable classifications. In CVPR, pages 10029- 10038, June 2021.","title":"Convolutional dynamic alignment networks for interpretable classifications","authors":"Mario Moritz Bohle, Bernt Fritz, Schiele","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Böhle et al., 2022] Moritz Böhle, Mario Fritz, and Bernt Schiele. B-cos networks: Alignment is all we need for interpretability. In CVPR, pages 10329-10338, June 2022.","title":"B-cos networks: Alignment is all we need for interpretability","authors":"Mario Moritz Böhle, Bernt Fritz, Schiele","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Bonassi et al., 2021] Fabio Bonassi, Marcello Farina, and Riccardo Scattolini. On the stability properties of gated recurrent units neural networks. Systems & Control Let- ters, 157:105049, 2021.","title":"On the stability properties of gated recurrent units neural networks","authors":"Fabio Bonassi, Marcello Farina, Riccardo Scattolini","year":"2021","venue":"Systems & Control Letters","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Brendel and Bethge, 2019] Wieland Brendel and Matthias Bethge. Approximating CNNs with bag-of-local-features models works surprisingly well on imagenet. In ICLR, 2019.","title":"Approximating CNNs with bag-of-local-features models works surprisingly well on imagenet","authors":"Wieland Brendel, Matthias Bethge","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Chattopadhyay et al., 2022] Aditya Chattopadhyay, Stewart Slocum, Benjamin D. Haeffele, Rene Vidal, and Donald Geman. Interpretable by design: Learning predictors by composing interpretable queries, 2022. https://arxiv.org/ abs/2207.00938.","title":"Interpretable by design: Learning predictors by composing interpretable queries","authors":"Aditya Chattopadhyay, Stewart Slocum, Benjamin D Haeffele, Rene Vidal, Donald Geman","year":"2022","venue":null,"doi":null,"url":"https://arxiv.org/abs/2207.00938","internal_url":null},{"position":13,"raw":"[Chen et al., 2017] Shaofeng Chen, Yang Cao, Yu Kang, Rongrong Zhu, and Pengfei Li. Deep CNN Identifier for Dynamic Modelling of Unmanned Helicopter. In NeurIPS, pages 51-60, Cham, 2017.","title":"Deep CNN Identifier for Dynamic Modelling of Unmanned Helicopter","authors":"Shaofeng Chen, Yang Cao, Yu Kang, Rongrong Zhu, Pengfei Li","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Chen et al., 2019] Chaofan Chen, Oscar Li, Daniel Tao, Alina Barnett, Cynthia Rudin, and Jonathan K Su. This looks like that: Deep learning for interpretable image recognition. In NeurIPS, volume 32.","title":"This looks like that: Deep learning for interpretable image recognition","authors":"Chen","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"Curran Associates, Inc., 2019.","title":null,"authors":"Curran Associates, Inc","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Du et al., 2020] Yingwei Du, Fangzhou Liu, Jianbin Qiu, and Martin Buss. A semi-supervised learning approach for identification of piecewise affine systems. IEEE Trans. on Circuits and Systems I, 67(10):3521-3532, 2020.","title":"A semi-supervised learning approach for identification of piecewise affine systems","authors":"Du","year":"2020","venue":"IEEE Trans. on Circuits and Systems I","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Genc, 2017] Sahika Genc. Parametric system identifica- tion using deep convolutional neural networks. In IJCNN, pages 2112-2119, 2017.","title":"Parametric system identification using deep convolutional neural networks","authors":"Sahika Genc, Genc","year":"2017","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Guidotti and Ruggieri, 2019] Riccardo Guidotti and Salva- tore Ruggieri. On the stability of interpretable models. In IJCNN, pages 1-8, 2019.","title":"On the stability of interpretable models","authors":"Ruggieri Guidotti, Riccardo Guidotti, Salvatore Ruggieri","year":"2019","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Hojjatinia et al., 2020] Sarah Hojjatinia, Constantino M. Lagoa, and Fabrizio Dabbene. Identification of switched autoregressive exogenous systems from large noisy datasets. Int. J. Robust and Nonlinear Control, 30(15):5777-5801, 2020.","title":"Identification of switched autoregressive exogenous systems from large noisy datasets","authors":"Sarah Hojjatinia, M Constantino, Fabrizio Lagoa, Dabbene","year":"2020","venue":"Int. J. Robust and Nonlinear Control","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Jinil and Reka, 2019] Nectar Jinil and Sofana Reka. Deep learning method to predict electric vehicle power require- ments and optimizing power distribution. In ICEES, pages 1-5, 2019.","title":"Nectar Jinil and Sofana Reka. Deep learning method to predict electric vehicle power requirements and optimizing power distribution","authors":"Reka Jinil","year":"2019","venue":"ICEES","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Krishnapriyan et al., 2021] Aditi Krishnapriyan, Amir Gholami, Shandian Zhe, Robert Kirby, and Michael W. Mahoney. Characterizing possible failure modes in physics-informed neural networks. In NeurIPS, 2021.","title":"Characterizing possible failure modes in physics-informed neural networks","authors":"Aditi Krishnapriyan, Amir Gholami, Shandian Zhe, Robert Kirby, Michael W Mahoney","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lauer, 2013] Fabien Lauer. Estimating the probability of success of a simple algorithm for switched linear regres- sion. Nonlinear Analysis: Hybrid Systems, 8:31-47, 2013.","title":"Estimating the probability of success of a simple algorithm for switched linear regression","authors":"Fabien Lauer","year":"2013","venue":"Nonlinear Analysis: Hybrid Systems","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Lauer, 2015] Fabien Lauer. On the complexity of piecewise affine system identification. Automatica, 62(C):148-153, 2015.","title":"On the complexity of piecewise affine system identification","authors":"Fabien Lauer","year":"2015","venue":"Automatica","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Letzgus et al., 2022] Simon Letzgus, Patrick Wagner, Jonas Lederer, Wojciech Samek, Klaus-Robert Müller, and Grégoire Montavon. Toward Explainable Artificial In- telligence for Regression Models: A methodological per- spective. IEEE Signal Processing Magazine, 39(4):40-58, 2022.","title":"Toward Explainable Artificial Intelligence for Regression Models: A methodological perspective","authors":"Simon Letzgus, Patrick Wagner, Jonas Lederer, Wojciech Samek, Klaus-Robert Müller, Grégoire Montavon","year":"2022","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Li et al., 2017] Guoyuan Li, Bikram Kawan, Hao Wang, and Houxiang Zhang. Neural-network-based modelling and analysis for time series prediction of ship motion. Ship Technology Research, 64, 2017.","title":"Neural-network-based modelling and analysis for time series prediction of ship motion","authors":"Guoyuan Li, Bikram Kawan, Hao Wang, Houxiang Zhang","year":"2017","venue":"Ship Technology Research","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Li et al., 2019] Kai Li, Jiaqing Kou, and Weiwei Zhang. Deep neural network for unsteady aerodynamic and aeroe- lastic modeling across multiple mach numbers. Nonlinear Dynamics, 96:1-21, 2019.","title":"Deep neural network for unsteady aerodynamic and aeroelastic modeling across multiple mach numbers","authors":"Kai Li, Jiaqing Kou, Weiwei Zhang","year":"2019","venue":"Nonlinear Dynamics","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Lin and Antsaklis, 2009] Hai Lin and Panos J. Antsaklis. Stability and stabilizability of switched linear systems: A survey of recent results. IEEE Trans. Automatic Control, 54(2):308-322, 2009.","title":"Stability and stabilizability of switched linear systems: A survey of recent results","authors":"Hai Lin, Panos J Antsaklis","year":"2009","venue":"IEEE Trans. Automatic Control","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Lundberg and Lee, 2017] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In NeurIPS, volume 30.","title":"A unified approach to interpreting model predictions","authors":"M Scott, Su-In Lundberg, Lee","year":null,"venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"Curran Associates, Inc., 2017.","title":null,"authors":"Curran Associates, Inc","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Ma and Qu, 2020] Lijing Ma and Shiru Qu. A se- quence to sequence learning based car-following model for multi-step predictions considering reaction delay. Transportation Research Part C: Emerging Technologies, 120:102785, 2020.","title":"Lijing Ma and Shiru Qu. A sequence to sequence learning based car-following model for multi-step predictions considering reaction delay","authors":"Qu Ma","year":"2020","venue":"Transportation Research Part C: Emerging Technologies","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Marcos et al., 2020] Diego Marcos, Ruth Fong, Sylvain Lo- bry, Remi Flamary, Nicolas Courty, and Devis Tuia. Con- textual semantic interpretability. In ACCV, November 2020.","title":"Contextual semantic interpretability","authors":"Marcos","year":"2020","venue":"ACCV","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Massucci et al., 2021] Louis Massucci, Fabien Lauer, and Marion Gilson. Regularized switched system iden- tification: a statistical learning perspective. IFAC- PapersOnLine, 54(5):55-60, 2021. 7th IFAC Conference on Analysis and Design of Hybrid Systems ADHS 2021.","title":"Regularized switched system identification: a statistical learning perspective","authors":"Massucci","year":"2021","venue":"IFAC Conference on Analysis and Design of Hybrid Systems ADHS","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Mayne et al., 2000] D.Q. Mayne, J.B. Rawlings, C.V. Rao, and P.O.M. Scokaert. Constrained model predictive con- trol: Stability and optimality. Automatica, 36(6):789-814, 2000.","title":"Constrained model predictive control: Stability and optimality","authors":"D Q Mayne, J B Rawlings, C V Rao, P O M Scokaert","year":"2000","venue":"Automatica","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Mejari et al., 2020] Manas Mejari, Vihangkumar V. Naik, Dario Piga, and Alberto Bemporad. Identification of hy- brid and linear parameter-varying models via piecewise affine regression using mixed integer programming. Int. J. Robust and Nonlinear Control, 30(15):5802-5819, 2020.","title":"Identification of hybrid and linear parameter-varying models via piecewise affine regression using mixed integer programming","authors":"Manas Mejari, V Vihangkumar, Dario Naik, Alberto Piga, Bemporad","year":"2020","venue":"Int. J. Robust and Nonlinear Control","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Mohajerin and Rohani, 2019] Nima Mohajerin and Mohsen Rohani. Multi-step prediction of occupancy grid maps with recurrent neural networks. In CPVR, June 2019.","title":"Multi-step prediction of occupancy grid maps with recurrent neural networks","authors":"Rohani Mohajerin, Nima Mohajerin, Mohsen Rohani","year":"2019","venue":"CPVR","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Mohajerin and Waslander, 2019] Nima Mohajerin and Steven L. Waslander. Multistep prediction of dynamic systems with recurrent neural networks. IEEE TNNLS, 30(11):3370-3383, 2019.","title":"Multistep prediction of dynamic systems with recurrent neural networks","authors":"Nima Mohajerin, Steven L Waslander","year":"2019","venue":"IEEE TNNLS","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Nauta et al., 2021] Meike Nauta, Ron van Bree, and Christin Seifert. Neural prototype trees for interpretable fine-grained image recognition. In CVPR, pages 14933- 14943, June 2021.","title":"Neural prototype trees for interpretable fine-grained image recognition","authors":"Meike Nauta, Ron Van Bree, Christin Seifert","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Nguyen and Martínez, 2020] An-phi Nguyen and María Rodríguez Martínez. On quantitative aspects of model interpretability. CoRR, abs/2007.07584, 2020.","title":"An-phi Nguyen and María Rodríguez Martínez. On quantitative aspects of model interpretability","authors":"Martínez Nguyen","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Pauli et al., 2022] Patricia Pauli, Anne Koch, Julian Berberich, Paul Kohler, and Frank Allgöwer. Training robust neural networks using lipschitz bounds. IEEE Control Systems Letters, 6:121-126, 2022.","title":"Training robust neural networks using lipschitz bounds","authors":"Patricia Pauli, Anne Koch, Julian Berberich, Paul Kohler, Frank Allgöwer","year":"2022","venue":"IEEE Control Systems Letters","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Punjani and Abbeel, 2015] Ali Punjani and Pieter Abbeel. Deep learning helicopter dynamics models. In ICRA, pages 3223-3230, 2015.","title":"Deep learning helicopter dynamics models","authors":"Abbeel Punjani, Ali Punjani, Pieter Abbeel","year":"2015","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Revay et al., 2021] Max Revay, Ruigang Wang, and Ian R. Manchester. A convex parameterization of robust recurrent neural networks. In ACC, pages 2824-2829, 2021.","title":"A convex parameterization of robust recurrent neural networks","authors":"Revay","year":"2021","venue":"ACC","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Ribeiro et al., 2016] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. \"Why Should I Trust You?\": Ex- plaining the Predictions of Any Classifier. In ACM SIGKDD, KDD '16, page 1135-1144, 2016.","title":"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","authors":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":"ACM SIGKDD, KDD '16","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Schlegel et al., 2021] Udo Schlegel, Duy Lam Vo, Daniel A. Keim, and Daniel Seebacher. TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models. In Machine Learning and Principles and Practice of Knowledge Discovery in Databases, pages 5-14, Cham, 2021.","title":"TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models","authors":"Udo Schlegel, Duy Lam Vo, Daniel A Keim, Daniel Seebacher","year":"2021","venue":"Machine Learning and Principles and Practice of Knowledge Discovery in Databases","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Schürholz et al., 2019] Klemens Schürholz, Daniel Brückner, and Dirk Abel. Modelling the Exhaust Gas Aftertreatment System of a SI Engine Using Artificial Neural Networks. Topics in Catalysis, 62, 2019.","title":"Modelling the Exhaust Gas Aftertreatment System of a SI Engine Using Artificial Neural Networks","authors":"Klemens Schürholz, Daniel Brückner, Dirk Abel","year":"2019","venue":"Topics in Catalysis","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Sefidmazgi et al., 2015] Mohammad Gorji Sefidmazgi, Mina Moradi Kordmahalleh, Abdollah Homaifar, and Ali Karimoddini. Switched linear system identification based on bounded-switching clustering. In ACC, pages 1806-1811, 2015.","title":"Switched linear system identification based on bounded-switching clustering","authors":"Mohammad Gorji, Sefidmazgi, Mina Moradi Kordmahalleh, Abdollah Homaifar, Ali Karimoddini","year":"2015","venue":"ACC","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Turk et al., 2018] D. Turk, J. Gillis, G. Pipeleers, and J. Sw- evers. Identification of linear parameter-varying systems: A reweighted l2,1-norm regularization approach. Mechan- ical Systems and Signal Processing, 100:729-742, 2018.","title":"Identification of linear parameter-varying systems: A reweighted l2,1-norm regularization approach","authors":"D Turk, J Gillis, G Pipeleers, J Swevers","year":"2018","venue":"Mechanical Systems and Signal Processing","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Wei et al., 2022] Yunyu Wei, Zezong Chen, Chen Zhao, Yuanhui Tu, Xi Chen, and Rui Yang. An ensemble multi- step forecasting model for ship roll motion under different external conditions: A case study on the South China Sea. Measurement, 201:111679, 2022.","title":"An ensemble multistep forecasting model for ship roll motion under different external conditions: A case study on the South China Sea","authors":"Yunyu Wei, Zezong Chen, Chen Zhao, Yuanhui Tu, Xi Chen, Rui Yang","year":"2022","venue":"Measurement","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[wei Gao et al., 2021] Da wei Gao, Yong sheng Zhu, Jin fen Zhang, Yan kang He, Ke Yan, and Bo ran Yan. A novel MP-LSTM method for ship trajectory prediction based on AIS data. Ocean Engineering, 228:108956, 2021.","title":"A novel MP-LSTM method for ship trajectory prediction based on AIS data","authors":"Wei Gao","year":"2021","venue":"Ocean Engineering","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Weigand et al., 2021] Jonas Weigand, Michael Deflorian, and Martin Ruskowski. Input-to-state stability for sys- tem identification with continuous-time runge-kutta neu- ral networks. Int. J. Control, 0(0):1-17, 2021.","title":"Input-to-state stability for system identification with continuous-time runge-kutta neural networks","authors":"Weigand","year":"2021","venue":"Int. J. Control","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Weigand et al., 2022] Jonas Weigand, Julian Götz, Jonas Ulmen, and Martin Ruskowski. Dataset and baseline for an industrial robot identification benchmark. https: //doi.org/10.26204/data/5, 2022. Accessed: 2023-06-05.","title":"Dataset and baseline for an industrial robot identification benchmark","authors":"Weigand","year":"2022","venue":null,"doi":"10.26204/data/5","url":"https://doi.org/10.26204/data/5,2022","internal_url":null},{"position":51,"raw":"[Woo et al., 2018] Joohyun Woo, Jongyoung Park, Chanwoo Yu, and Nakwan Kim. Dynamic model identification of unmanned surface vehicles using deep learning network. Applied Ocean Research, 78:123-133, 2018.","title":"Dynamic model identification of unmanned surface vehicles using deep learning network","authors":"Woo","year":"2018","venue":"Applied Ocean Research","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Wu et al., 2020] Zhe Wu, David Rincon, and Panagiotis Christofides. Process structure-based recurrent neural net- work modeling for model predictive control of nonlinear processes. J. Process Control, 89:74-84, 05 2020.","title":"Process structure-based recurrent neural network modeling for model predictive control of nonlinear processes","authors":"Zhe Wu, David Rincon, Panagiotis Christofides","year":"2020","venue":"J. Process Control","doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Wu et al., 2021] Mike Wu, Sonali Parbhoo, Michael C Hughes, Volker Roth, and Finale Doshi-Velez. Optimiz- ing for interpretability in deep neural networks with tree regularization. J. Artificial Intelligence Research, 72:1- 37, 2021.","title":"Optimizing for interpretability in deep neural networks with tree regularization","authors":"Mike Wu, Sonali Parbhoo, C Michael, Volker Hughes, Finale Roth, Doshi-Velez","year":"2021","venue":"J. Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Yeh et al., 2019] Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Sai Suggala, David I. Inouye, and Pradeep Raviku- mar. On the (in)fidelity and sensitivity of explanations. In NeurIPS, 2019.","title":"Inouye, and Pradeep Ravikumar. On the (in)fidelity and sensitivity of explanations","authors":"Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Sai Suggala, I David","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Zhai et al., 2002] Guisheng Zhai, Bo Hu, K. Yasuda, and A.N. Michel. Qualitative analysis of discrete-time switched systems. In ACC, volume 3, pages 1880-1885 vol.3, 2002.","title":"Qualitative analysis of discrete-time switched systems","authors":"Guisheng Zhai, Bo Hu, K Yasuda, A N Michel","year":"2002","venue":"ACC","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}