Results 81 to 90 of about 780 (160)

Loss Terms and Operator Forms of Koopman Autoencoders

CoRR
Koopman autoencoders are a prevalent architecture in operator learning. But, the loss functions and the form of the operator vary significantly in the literature. This paper presents a fair and systemic study of these options. Furthermore, it introduces novel loss terms.
Dustin Enyeart, Guang Lin 0001
openaire   +2 more sources

Koopman fault‐tolerant model predictive control

IET Control Theory & Applications
This paper introduces a novel data‐driven approach to develop a fault‐tolerant model predictive controller (MPC) for non‐linear systems. By adopting a Koopman operator‐theoretic perspective, the proposed method leverages historical data from the system ...
Mohammadhosein Bakhtiaridoust, Meysam Yadegar, Fatemeh Jahangiri   +2 more
doaj   +1 more source

Optimal Control of Entity-Based Systems via Koopman Representations With Product Density Observables

IEEE Open Journal of Control Systems
The Koopman operator, which describes a dynamical system via a linear representation that can be approximately learned from data, allows application of linear control techniques to nonlinear systems.
Madeline Blischke, Joao P. Hespanha
doaj   +1 more source

Adversarial dynamical systems characterize when data-driven learning succeeds or fails

Nature Communications
Many systems resist analytical modeling, making data-driven inference of dynamics important. Yet data-driven methods can fail to converge or generalize, leaving open a central question: When can system behavior be learned reliably from data, and when is ...
Matthew J. Colbrook, Igor Mezić, Alexei Stepanenko   +2 more
doaj   +1 more source

Understanding Brain Functional Dynamics Through Neural Koopman Operator With Control Mechanism. [PDF]

IEEE Trans Med Imaging
Zhou Z, Dan T, Wu G.
europepmc   +1 more source

A Koopman operator-based prediction algorithm and its application to COVID-19 pandemic and influenza cases. [PDF]

Sci Rep
Mezić I, Drmač Z, Črnjarić N, Maćešić S, Fonoberova M, Mohr R, Avila AM, Manojlović I, Andrejčuk A.   +8 more
europepmc   +1 more source

Online real-time learning of dynamical systems from noisy streaming data. [PDF]

Sci Rep, 2023
Sinha S, Nandanoori SP, Barajas-Solano DA.   +2 more
europepmc   +1 more source

Koopman-von Neumann and Weyl-Wigner Phase-Space Formulation of Inviscid Euler Flows. [PDF]

Entropy (Basel)
Molnar SM, Godfrey JR.
europepmc   +1 more source

Koopman mode decomposition of thermodynamic dissipation in nonlinear Langevin dynamics. [PDF]

Proc Natl Acad Sci U S A
Sekizawa D, Ito S, Oizumi M.
europepmc   +1 more source

Intermittent Two-Point Dynamics at the Transition to Chaos for Random Circle Endomorphisms. [PDF]

Commun Math Phys
Goverse VPH, Homburg AJ, Lamb JSW.
europepmc   +1 more source