Results 111 to 120 of about 57,420 (165)

Robustness of radial basis functions

Neurocomputing, 2005
Neural networks are intended to be used in future nanoelectronic technology since these architectures seem to be robust to malfunctioning elements and noise in its inputs and parameters. In this work, the robustness of radial basis function networks is analyzed in order to operate in noisy and unreliable environment.
Eickhoff, Ralf, Rückert, Ulrich
openaire   +2 more sources

Adaptive radial basis functions

Proceedings of 13th International Conference on Pattern Recognition, 1996
We develop adaptive radial basis functions: kernel-based models for regression and discrimination where the functional form of the basis function depends on the data. The approach may be regarded as a radial form of projection pursuit, with the additional constraint that the basis functions have a common functional form.
Andrew R. Webb, Simon Shannon
openaire   +1 more source

Multi-layer radial basis function networks. An extension to the radial basis function

Proceedings of International Conference on Neural Networks (ICNN'96), 2002
This paper presents the initial research carried out into a new neural network called the multilayer radial basis function network (MRBF). The network extends the radial basis function (RBF) in a similar way to that in which the multilayer perceptron extends the perceptron.
R. J. Craddock, K. Warwick
openaire   +1 more source

Radial Basis Functions

Acta Numerica, 2000
Radial basis function methods are modern ways to approximate multivariate functions, especially in the absence of grid data. They have been known, tested and analysed for several years now and many positive properties have been identified. This paper gives a selective but up-to-date survey of several recent developments that explains their ...
openaire   +1 more source

On radial basis functions

2019
Many sciences and other areas of research and applications from engineering to economics require the approximation of functions that depend on many variables. This can be for a variety of reasons. Sometimes we have a discrete set of data points and we want to find an approximating function that completes this data; another possibility is that precise ...
Buhmann, Martin, Jäger, Janin
openaire   +2 more sources

STOCHASTIC RADIAL BASIS FUNCTIONS

International Journal of Neural Systems, 2001
Stochastic signal processing can implement gaussian activation functions for radial basis function networks, using stochastic counters. The statistics of neural inputs which control the increment and decrement operations of the counter are governed by Bernoulli distributions. The transfer functions relating the input and output pulse probabilities can
openaire   +2 more sources

Deformable Radial Basis Functions

2007
Radial basis function networks (RBF) are efficient general function approximators. They show good generalization performance and they are easy to train. Due to theoretical considerations RBFs commonly use Gaussian activation functions. It has been shown that these tight restrictions on the choice of possible activation functions can be relaxed in ...
Wolfgang Hübner 0003, Hanspeter A. Mallot   +1 more
openaire   +1 more source

Comparison of Radial Basis Functions

Numerical Analysis and Applications, 2018
Summary: A survey of algorithms for approximation of multivariate functions with radial basis function (RBF) splines is presented. Algorithms of interpolating, smoothing, selecting the smoothing parameter, and regression with splines are described in detail.
openaire   +2 more sources

Applying radial basis functions

IEEE Signal Processing Magazine, 1996
Discusses the application of neural networks to general and radial basis functions and in particular to adaptive equalization and interference rejection problems. Neural-network-based algorithms strike a good balance between performance and complexity in adaptive equalization, and show promise in spread spectrum systems.
openaire   +1 more source

Radial Basis Functions

2001
In classical signal processing, we typically consider a single-input single-output (SISO) discretetime, causal, infinite-dimensional, time-invariant dynamical system described by y(t) = ∞σ k=p h(k)x(t - k)+ v(t) (3.1) where {h(k)} ε 1 is a weighting sequence, {v(t)} is a disturbance sequence of zero-mean, independent and identically distributed random ...
openaire   +2 more sources