scholar.google.com › citations
The performance of the various neural networks is analyzed and validated via some well-known benchmark problems as target functions, such as Sphere, Rastrigin, ...
In this paper, we apply three types of well-known neural networks namely Back Propagation (BP), Radial Basis Function (RDF) and Generalized Regression (GN) to ...
The experimental results show that among the three neural networks tested, Radial Basis Function (RBF) neural network is superior in terms of speed and accuracy ...
A model which takes advantage of wavelet-like functions in the functional form of a neural network is used for function approximation.
People also ask
How do neural networks approximate functions?
Why 2 layer neural networks can approximate any function?
Which of the following networks are generally used for function approximation problems?
What is universal approximation of neural networks for function approximation regression?
Aug 27, 2020 · Function approximation is a technique for estimating an unknown underlying function using historical or available observations from the domain.
Missing: Investigation | Show results with:Investigation
Abstract: A study of the approximation capabilities of single hidden layer neural networks leads to a strong motivation for investigating constructive ...
Jan 19, 2022 · The problem of function approximation with neural networks has been of big interest in mathematical research for the last several decades.
Missing: Investigation | Show results with:Investigation
Sep 7, 2023 · Basically, I want a neural network to learn the simple polynomial pattern of a set of arrays of the form [x,y], with y = x², where the first ...
Missing: Investigation | Show results with:Investigation
Dec 28, 2020 · This article surveys the known approximation properties of the outputs of NNs with the aim of uncovering the properties that are not present in ...
Duration: 44:02
Posted: Dec 21, 2021
Posted: Dec 21, 2021
Missing: Investigation | Show results with:Investigation