Results 11 to 20 of about 71,359 (311)
Deep Residual Learning for Nonlinear Regression
Entropy, 2020 Deep learning plays a key role in the recent developments of machine learning. This paper develops a deep residual neural network (ResNet) for the regression of nonlinear functions.
Dongwei Chen +3 more
doaj +1 more source
Nonlinear Knowledge in Kernel Approximation [PDF]
IEEE Transactions on Neural Networks, 2007 Prior knowledge over arbitrary general sets is incorporated into nonlinear kernel approximation problems in the form of linear constraints in a linear program. The key tool in this incorporation is a theorem of the alternative for convex functions that converts nonlinear prior knowledge implications into linear inequalities without the need to ...
Olvi L. Mangasarian, Edward W. Wild
openaire +2 more sources
Nonlinear Bivariate Bernstein–Chlodowsky Operators of Maximum Product Type
Journal of Mathematics, 2022 The positive nonlinear operators with maximum and product were introduced by Bede. In this study, nonlinear maximum product type of bivariate Bernstein–Chlodowsky operators is defined and the approximation properties are investigated with the help of new
Özge Özalp Güller +2 more
doaj +1 more source
On the Approximation of Moments for Nonlinear Systems [PDF]
IEEE Transactions on Automatic Control, 2021 Model reduction by moment-matching relies upon the availability of the so-called moment . If the system is nonlinear, the computation of moments depends on an underlying specific invariance equation, which can be difficult or impossible to solve. This article presents four technical contributions related to the theory of moment matching: first, we ...
Nicolás Faedo +3 more
openaire +5 more sources
The complexity of approximating a nonlinear program [PDF]
Mathematical Programming, 1993 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Mihir Bellare, Phillip Rogaway
openaire +1 more source
A nonlinear quantum adiabatic approximation [PDF]
Nonlinearity, 2020 Abstract This paper is devoted to a generalisation of the quantum adiabatic theorem to a nonlinear setting. We consider a Hamiltonian operator which depends on the time variable and on a finite number of parameters and acts on a separable Hilbert space of which we select a fixed basis.
Fermanian Kammerer, Clotilde +1 more
openaire +3 more sources
Complexity, 2022 In this paper, some novel analytical and numerical techniques are introduced for solving and analyzing nonlinear second-order ordinary differential equations (ODEs) that are associated to some strongly nonlinear oscillators such as a quadratically damped
Alvaro H. Salas +3 more
doaj +1 more source
Results in Physics, 2021 The derivation of a nonlinear ordinary differential equation for modeling the nonlinear oscillations of a gas bubble placed in an ultrasonic field is performed in terms of bubble-volume variations up to the fourth-order approximation.
Christian Vanhille
doaj +1 more source
Nonlinear Approximation with Redundant Dictionaries [PDF]
Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005., 2006 In this paper we study nonlinear approximation and data representation with redundant function dictionaries. In particular, approximation with redundant wavelet bi-frame systems is studied in detail. Several results for orthonormal wavelets are generalized to the redundant case. In general, for a wavelet bi-frame system the approximation properties are
Borup, Lasse +2 more
openaire +2 more sources
On the stability of a class of essentially nonlinear difference systems
Vestnik Samarskogo Gosudarstvennogo Tehničeskogo Universiteta. Seriâ: Fiziko-Matematičeskie Nauki, 2012 The problem of the zero solution stability for a certain class of essentially nonlinear difference systems is studied. Theorems on the stability by the inhomogeneous approximation are proved.
A. A. Sultanbekov
doaj +3 more sources