Results 1  10
of
1,291
Evolutionary optimization of RBF networks
 in Proc. 6th Brazilian Symp. Neural Networks, Rio de Janeiro
, 2000
"... One of the main obstacles to the widespread use of artijcial neural networks is the difJiculty of adequately define values for their free parameters. This article discusses how Radial Basis Function, RBF; networks can have their parameters defined by genetic algorithms. For such, it presents an ov ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
One of the main obstacles to the widespread use of artijcial neural networks is the difJiculty of adequately define values for their free parameters. This article discusses how Radial Basis Function, RBF; networks can have their parameters defined by genetic algorithms. For such, it presents
Automatic Generation of RBF Networks
, 1995
"... Learning can be viewed as mapping from an input space to an output space. Examples of these mappings are used to construct a continuous function that approximates the given data and generalizes for intermediate instances. Radial basis function (RBF) networks are used to formulate this approximating ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
Learning can be viewed as mapping from an input space to an output space. Examples of these mappings are used to construct a continuous function that approximates the given data and generalizes for intermediate instances. Radial basis function (RBF) networks are used to formulate this approximating
RBF Networks for Object Recognition
 Center for Cognitive Sciences, Bremen University
, 1995
"... A predominant task occurring in Computer Vision is to localize and recognize the twodimensional view of an object in the image. In particular, for controlling our vision based roboter system autonomous object detection is necessary for grasping scene objects. The work being reported here uses RBF n ..."
Abstract

Cited by 4 (3 self)
 Add to MetaCart
A predominant task occurring in Computer Vision is to localize and recognize the twodimensional view of an object in the image. In particular, for controlling our vision based roboter system autonomous object detection is necessary for grasping scene objects. The work being reported here uses RBF
Robust RBF Networks
"... Introduction Radial Basis Functions (RBF) have been used in several applications for functional modeling and pattern classification. They have been found to have very good functional approximation capabilities. It has been proven that any continuous function can be modeled up to a certain precision ..."
Abstract
 Add to MetaCart
by a set of radial basis functions [1], [2], [3]. RBFs have their fundamentals drawn from probability function estimation theory. RBF network consists of a two layer feedforward neural network. The hidden units implement functions which geometrically have a radial activation region similar
RBF Networks from Boosted Rules
"... A novel method for constructing RBF networks is presented. It is based on Boosting, an ensemble method that combines several classifiers obtained using any other classification method. If the classifiers that are going to be combined by boosting are radialbasis functions, then the boosting method pr ..."
Abstract
 Add to MetaCart
A novel method for constructing RBF networks is presented. It is based on Boosting, an ensemble method that combines several classifiers obtained using any other classification method. If the classifiers that are going to be combined by boosting are radialbasis functions, then the boosting method
Fast learning with incremental RBF Networks
 Neural Processing Letters
, 1994
"... We present a new algorithm for the construction of radial basis function (RBF) networks. The method uses accumulated error information to determine where to insert new units. The diameter of the localized units is chosen based on the mutual distances of the units. To have the distance information al ..."
Abstract

Cited by 50 (7 self)
 Add to MetaCart
We present a new algorithm for the construction of radial basis function (RBF) networks. The method uses accumulated error information to determine where to insert new units. The diameter of the localized units is chosen based on the mutual distances of the units. To have the distance information
Global Optimization of RBF Networks
, 2001
"... Several modifications to parameter estimation in a Radial Basis Functions network are introduced. These include a better initializing clustering algorithm and a full gradient descent on centers and weights after weights were found via a matrix inversion. Performance comparison with other RBF algorit ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Several modifications to parameter estimation in a Radial Basis Functions network are introduced. These include a better initializing clustering algorithm and a full gradient descent on centers and weights after weights were found via a matrix inversion. Performance comparison with other RBF
Learning Classification RBF Networks by Boosting
"... This work proposes a novel method for constructing RBF networks, based on boosting. The task assigned to the base learner is to select a RBF, while the boosting algorithm combines linearly the different RBFs. For each iteration of boosting a new neuron is incorporated into the network. ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
This work proposes a novel method for constructing RBF networks, based on boosting. The task assigned to the base learner is to select a RBF, while the boosting algorithm combines linearly the different RBFs. For each iteration of boosting a new neuron is incorporated into the network.
An optimized RBF network for approximation of functions
, 1994
"... Abstract. RBF networks are widely used for the nonparametric estimation of realvalued multidimentional functions through a finite set of samples This paper describes a method to compute the parameters of a RBF network with Gaussian kernels, namely their locations, widths and weights; the paramete ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
Abstract. RBF networks are widely used for the nonparametric estimation of realvalued multidimentional functions through a finite set of samples This paper describes a method to compute the parameters of a RBF network with Gaussian kernels, namely their locations, widths and weights
A probabilistic RBF network for classification
 in Proc. Int. Joint Conf NeuralNenvorks
, 2000
"... Abstract We present a probabilistic neural network model which is suitable for classification problems.This model constitutes an adaptation of the classical RBF network where the outputs represent the class conditional distributions. Since the network outputs correspond to probability densities fun ..."
Abstract

Cited by 5 (4 self)
 Add to MetaCart
Abstract We present a probabilistic neural network model which is suitable for classification problems.This model constitutes an adaptation of the classical RBF network where the outputs represent the class conditional distributions. Since the network outputs correspond to probability densi
Results 1  10
of
1,291