Results 31 to 40 of about 1,569,596 (297)

Universal meromorphic approximation [PDF]

, 2011
Das erste Beispiel einer so genannten universellen holomorphen Funktion stammt von Birkhoff, welcher im Jahre 1929 die Existenz einer ganzen Funktion beweisen konnte, die gewissermaßen jede ganze Funktion durch geeignete Translationen approximieren kann.
Meyrath, Thierry
core   +1 more source

Why neural networks apply to scientific computing?

Theoretical and Applied Mechanics Letters, 2021
In recent years, neural networks have become an increasingly powerful tool in scientific computing. The universal approximation theorem asserts that a neural network may be constructed to approximate any given continuous function at desired accuracy. The
Shaoqiang Tang, Yang Yang
doaj   +1 more source

Shorter quantum circuits via single-qubit gate approximation [PDF]

Quantum, 2023
We give a novel procedure for approximating general single-qubit unitaries from a finite universal gate set by reducing the problem to a novel magnitude approximation problem, achieving an immediate improvement in sequence length by a factor of 7/9 ...
Vadym Kliuchnikov, Kristin Lauter, Romy Minko, Adam Paetznick, Christophe Petit   +4 more
doaj   +1 more source

Disturbance observer-based control with adaptive neural network for unknown nonlinear system

Measurement + Control, 2023
This paper presents an adaptive neural network controller based on a disturbance observer to compensate the disturbance caused by neural network approximation for a class of unknown nonlinear systems.
Jing Hu, Meirong Zheng
doaj   +1 more source

Stable and Efficient Gaussian-Based Kolmogorov–Arnold Networks

Mathematics
Kolmogorov–Arnold Networks employ learnable univariate activation functions on edges rather than fixed node nonlinearities. Standard B-spline implementations require O(3KW) parameters per layer (K basis functions, W connections).
Pasquale De Luca, Emanuel Di Nardo, Livia Marcellino, Angelo Ciaramella   +3 more
doaj   +1 more source

Parametric method for unsteady two-dimensional MHD boundary-layer on a body for which temperature varies with time

Archives of Mechanics, 2011
This paper concerns unsteady two-dimensional laminar temperature magnetohydrodynamic (MHD) boundary-layer of incompressible fluid. The present magnetic field is homogenous and perpendicular to the body surface along which the boundary-layer is developing.
D. Nikodijevic, V. Nikolic, Z. Stamenkovic, A. Boricic   +3 more
doaj   +1 more source

Universal Approximation with Certified Networks

CoRR, 2019
ICLR ...
Baader, Maximilian; id_orcid0000-0002-9271-6422, Mirman, Matthew, Vechev, Martin   +2 more
openaire   +5 more sources

Universal Approximation and the Topological Neural Network

IEEE Access
A topological neural network (TNN), which takes input data from a Tychonoff topological space instead of the usual finite dimensional space, is introduced.
Michael A. Kouritzin, Daniel Richard
doaj   +1 more source

Universal Successor Features Approximators

CoRR, 2018
The ability of a reinforcement learning (RL) agent to learn about many reward functions at the same time has many potential benefits, such as the decomposition of complex tasks into simpler ones, the exchange of information between tasks, and the reuse of skills.
Diana Borsa, André Barreto 0001, John Quan, Daniel J. Mankowitz, Hado van Hasselt, Rémi Munos, David Silver 0001, Tom Schaul   +7 more
openaire   +3 more sources

Concurrent universal Padé approximation

, 2021
We prove concurrent universal Padé approximation for several universal Padé approximants of several types. Our results are generic in the space of holomorphic functions, in the space of formal power series as well as in a subspace of A∞.
Makridis, K., Nestoridis, V.
core   +1 more source