Results 11 to 20 of about 58,601 (260)
A Hybrid Regularization Operator and Its Application in Seismic Inversion
IEEE Access, 2021 Seismic inversion is an effective tool to estimate the properties of subsurface strata from seismograms. However, the intrinsic ill-posedness of the inversion problem causes the inverted subsurface properties to be easily polluted by inversion errors due
Yangting Liu +3 more
doaj +1 more source
Multi-parameter Tikhonov regularization [PDF]
Methods and Applications of Analysis, 2011 We study multi-parameter Tikhonov regularization, i.e., with multiple penalties. Such models are useful when the sought-for solution exhibits several distinct features simultaneously. Two choice rules, i.e., discrepancy principle and balancing principle, are studied for choosing an appropriate (vector-valued) regularization parameter, and some ...
Kazufumi Ito +2 more
openaire +2 more sources
Multi-Parameter Regularization Method for Synthetic Aperture Imaging Radiometers
Remote Sensing, 2021 Synthetic aperture imaging radiometers (SAIRs) are powerful passive microwave systems for high-resolution imaging by use of synthetic aperture technique.
Xiaocheng Yang +4 more
doaj +1 more source
IEEE Access, 2020 Generative adversarial networks (GANs) suffer from catastrophic forgetting when learning multiple consecutive tasks. Parameter regularization methods that constrain the parameters of the new model in order to be close to the previous model through ...
Yifan Chang +5 more
doaj +1 more source
Estimating the Regularization Parameter Efficiently [PDF]
Proceedings, 2018 We consider linear inverse problems with a two norm regularization, called Tikhonov regularization. When using regularization to solve an inverse problem, a regularization parameter is introduced. The regularization parameter heavily controls the quality of the regularized solution. We show various methods to estimate the regularization parameter known
N. Luiken (Nick) +1 more
openaire +2 more sources
Identification of Parameters in Distributed Parameter Systems by Regularization [PDF]
SIAM Journal on Control and Optimization, 1983 The authors investigate the parameter identification problem for distributed parameter systems. The problem of parameter identification in distributed parameter systems from noisy data is both nonlinear and ill- posed. They develop the concept of regularization, which is widely used in solving linear Fredholm integral equations, for the identification ...
Kravaris, Costas, Seinfeld, John H.
openaire +4 more sources
Regular Dependence of Total Variation on Parameters [PDF]
Real Analysis Exchange, 2004 If \(X\) is an interval, \(Y\) -- a metric space, \(T\) -- a set of parameters, and \(f: T\times X\to Y\) a function, then it can happen that \(f\) is measurable with respect to some \(\sigma\)-algebra while the function \(v:T\to X\), defined by \(v(t)\) equals to the total variation of \(f(t,\cdot)\), is not measurable.
Balcerzak, M., Kucia, A., Nowak, A.
openaire +3 more sources
Identification of the source for full parabolic equations
Mathematical Modelling and Analysis, 2021 In this work, we consider the problem of identifying the time independent source for full parabolic equations in Rn from noisy data. This is an ill-posed problem in the sense of Hadamard.
Guillermo Federico Umbricht
doaj +1 more source
Remote Sensing, 2020 Various types of heterogeneous observations can be combined within a parameter estimation process using spherical radial basis functions (SRBFs) for regional gravity field refinement.
Qing Liu +3 more
doaj +1 more source
Results in Physics, 2019 Extreme Learning Machine (ELM) is a single hidden layer feed-forward neural network with the learning speed is much faster than the traditional neural network architecture.
Shraddha M. Naik +2 more
doaj +1 more source