analiza aiqbench
This research introduces DissipNet, a novel architecture that integrates physical stability constraints directly into the neural network structure rather than relying solely on loss function penalties. By formally enforcing dissipativity through weight constraints and Lyapunov analysis, the model guarantees inherent stability for predicting real-world dynamical systems, addressing a critical limitation of standard Physics-Informed Neural Networks. This advancement represents a significant step toward robust Physical AI capable of safely controlling complex energy-dissipating processes.
Data-driven discrete-time deep recurrent neural network-based modeling for dissipative systems
arXiv:2609.27186v1 Announce Type: cross Abstract: Physical AI has gained increasing attention for its role in developing AI systems that better understand, predict, and control real-world dynamics. Achieving this requires AI models that not only achieve high prediction accuracy but also preserve fundamental physical properties of dynamical systems. In this paper, we propose a deep discrete-time dissipative recurrent neural network (DissipNet) that explicitly enforces dissipativity, a key property related to stability and energy dissipation, through structural weight constraints and a dedicated training algorithm. By construction, the proposed network is capable of learning dissipative dynamics while preserving their inherent stability, which is formally analyzed using Lyapunov theory. In contrast to Physics-Informed Neural Networks (PINNs), which incorporate governing equations into the training loss but do not guarantee preservation of internal analytical properties such as dissipativity or passivity, our approach provides explicit guarantees on stability at the model level. We demonstrate the effectiveness of the proposed method through several modeling applications, and compare its performance with a naive recurrent neural network (RNN) and a PINN-based model.
Abstract:Physical AI has gained increasing attention for its role in developing AI systems that better understand, predict, and control real-world dynamics. Achieving this requires AI models that not only achieve high prediction accuracy but also preserve fundamental physical properties of dynamical systems. In this paper, we propose a deep discrete-time dissipative recurrent neural network (DissipNet) that explicitly enforces dissipativity, a key property related to stability and energy dissipation, through structural weight constraints and a dedicated training algorithm. By construction, the proposed network is capable of learning dissipative dynamics while preserving their inherent stability, which is formally analyzed using Lyapunov theory. In contrast to Physics-Informed Neural Networks (PINNs), which incorporate governing equations into the training loss but do not guarantee preservation of internal analytical properties such as dissipativity or passivity, our approach provides explicit guarantees on stability at the model level. We demonstrate the effectiveness of the proposed method through several modeling applications, and compare its performance with a naive recurrent neural network (RNN) and a PINN-based model.
Machine Learning (cs.LG); Robotics (cs.RO)
arXiv:2609.27186 [cs.LG]
(or arXiv:2609.27186v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.27186 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.13140/RG.2.2.26658.80326 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 273 cuvinte
Subiecte conexe
Opaque recurrence, and other AI terms that you should probably know
TechCrunch · 7 sept. 2026
Frequency Selective Neural Networks as a Foundation Architecture for Time Series Learning
arXiv · 1 sept. 2026
Build an explainable next-best-product recommendation system for banking on AWS
AWS · 24 iul. 2026
Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
arXiv · 17 sept. 2026