Type of artificial neural network that uses radial basis functions as activation functions
In the field of mathematical modeling, a radial basis function network is an artificial neural network that uses radial basis functions as activation functions. The output of the network is a linear combination of radial basis functions of the inputs and neuron parameters. Radial basis function networks have many uses, including function approximation, time series prediction, classification, and system control. They were first formulated in a 1988 paper by Broomhead and Lowe, both researchers at the Royal Signals and Radar Establishment.[1][2][3]
^Broomhead, D. S.; Lowe, David (1988). Radial basis functions, multi-variable functional interpolation and adaptive networks (Technical report). RSRE. 4148. Archived from the original on April 9, 2013.
^Broomhead, D. S.; Lowe, David (1988). "Multivariable functional interpolation and adaptive networks" (PDF). Complex Systems. 2: 321–355. Archived (PDF) from the original on 2020-12-01. Retrieved 2019-01-29.
^Cite error: The named reference schwenker was invoked but never defined (see the help page).
and 26 Related for: Radial basis function network information
In mathematics a radialbasisfunction (RBF) is a real-valued function φ {\textstyle \varphi } whose value depends only on the distance between the input...
machine learning, a Hyper basisfunctionnetwork, or HyperBF network, is a generalization of radialbasisfunction (RBF) networks concept, where the Mahalanobis-like...
feedforward networks include convolutional neural networks and radialbasisfunctionnetworks, which use a different activation function. Hopfield network Feed-forward...
activation functions known as radialbasisfunctions (RBFs) are used in RBF networks, which are extremely efficient as universal function approximators...
feedforward networks. Radialbasisfunctions are functions that have a distance criterion with respect to a center. Radialbasisfunctions have been applied...
activation functions have been proposed, including the rectifier and softplus functions. More specialized activation functions include radialbasisfunctions (used...
Generalized regression neural network (GRNN) is a variation to radialbasis neural networks. GRNN was suggested by D.F. Specht in 1991. GRNN can be used...
generated sets of functions, such as the convolutional neural network (CNN) architecture, radialbasisfunctions, or neural networks with specific properties...
perhaps after transforming them through a radialbasisfunction (a technique that has been used to train RBF networks). Coates and Ng note that certain variants...
the embedded space. The mappings in NeuroScale are based on radialbasisfunctionnetworks. Gaussian process latent variable models (GPLVM) are probabilistic...
patterns in the feature space. Normal distribution Cauchy distribution Radialbasisfunction kernel Squires, G. L. (2001-08-30). Practical Physics (4 ed.). Cambridge...