Results 21 to 30 of about 906 (226)
Credit assignment for trained neural networks based on Koopman operator theory
Frontiers of Computer Science, 2023 Credit assignment problem of neural networks refers to evaluating the credit of each network component to the final outputs. For an untrained neural network, approaches to tackling it have made great contributions to parameter update and model revolution during the training phase.
Zhen Liang +5 more
openaire +2 more sources
Measurement + Control, 2022 The dynamic modeling and control of omni-directional mobile manipulators (OMM) are challenging since they are highly nonlinear, strongly coupled, and multi-input multi-output uncertainty systems.
Xuehong Zhu +5 more
doaj +1 more source
Optimizing Neural Networks via Koopman Operator Theory
CoRR, 2020 Koopman operator theory, a powerful framework for discovering the underlying dynamics of nonlinear dynamical systems, was recently shown to be intimately connected with neural network training. In this work, we take the first steps in making use of this connection.
Akshunna S. Dogra, William T. Redman
openaire +3 more sources
Identification of the Madden–Julian Oscillation With Data‐Driven Koopman Spectral Analysis
Geophysical Research Letters, 2023 The Madden‐Julian Oscillation (MJO), the dominant mode of tropical intraseasonal variability, is commonly identified using the realtime multivariate MJO (RMM) index based on joint empirical orthogonal function (EOF) analysis of near‐equatorial upper and ...
Benjamin R. Lintner +3 more
doaj +1 more source
Robot formation control in nonlinear manifold using Koopman operator theory [PDF]
Nonlinear Theory and Its Applications, IEICE, 2023 Formation control of multi-agent systems has been a prominent research topic, spanning both theoretical and practical domains over the past two decades. Our study delves into the leader-follower framework, addressing two critical, previously overlooked aspects.
Wang, Yanran +2 more
openaire +3 more sources
Extending the extended dynamic mode decomposition with latent observables: the latent EDMD framework
Machine Learning: Science and Technology, 2023 Bernard O Koopman proposed an alternative view of dynamical systems based on linear operator theory, in which the time evolution of a dynamical system is analogous to the linear propagation of an infinite-dimensional vector of observables.
Said Ouala +4 more
doaj +1 more source
Data-Driven Congestion Control of Micro Smart Sensor Networks for Transparent Substations
IEEE Access, 2021 Micro smart sensors and sensor networks are the key bases for building a fully visible, perceptible and controllable transparent substation in power grid.
Ke Zhou +3 more
doaj +1 more source
Koopman Operator for Nonlinear Flight Dynamics [PDF]
, 2022 Dynamical systems representing vehicle flight are inherently nonlinear. Currently there are no generalised frameworks for explicit characterisation and solution of such systems.
Bone, Viv, Jahn, Ingo, Lock, Andrew
core
Efficient Nonlinear Model Predictive Control of Automated Vehicles
Mathematics, 2022 In this paper, an efficient model predictive control (MPC) of velocity tracking of automated vehicles is proposed, in which a reference signal is given a priori.
Shuyou Yu +5 more
doaj +1 more source
Deep learning for Koopman operator approximations for control [PDF]
, 2021 The focus of this thesis is on combining the potential of Koopman operator theory with that of deep learning. This research topic has gained more and more interest in the scientific community in the last few years and is appealing for its great potential
Hader, Magdalena
core +2 more sources