A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation

By G. Huang, Paramasivan Saratchandran, Narasimhan Sundararajan. IEEE Transactions on Neural Networks, 2005

703 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/eac232320b09cecfb245c47602d7aba044a463b4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Fundamentals of natural computing: an overview (2007, background): “, networks whose architecture may increase and/or decrease in size [144,174,180]; ensembles of networks [228,289]; the investigation into formal aspects of ANNs, such as convergence and universal approximation capabilities [119,131,281]; hybrids between ANN and other approaches (e.”
Sequential Adaptive Fuzzy Inference System (SAFIS) for nonlinear system identification and prediction (2006, methodology): “An alternate way of calculating Einf(k) is by using the distribution of the inputs and follows the same approach as introduced in [7].”
A structure optimisation algorithm for feedforward neural network construction (2013, methodology): “It has been used in several papers, notably [21,34,35] to demonstrate the effect of a neural network algorithms”
Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes (2006, background): “have been proposed in the literature for training RBF networks [20]–[25], unlike our incremental learning algorithms, the universal approximation capability of these previous learning”
An efficient sequential learning algorithm for growing and pruning RBF (GAP-RBF) networks (2004, background): “For other general distributions like normal, Rayleigh, etc., the expressions for significance will be highly complex and are presented in Huang, et al. [10].”
Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm (2006, background): “A multilayer artificial neural network can approximate any nonlinear continuous function to an arbitrary accuracy [4]–[14].”
Extreme learning machines: a survey (2011, background): “resource allocation network and its variants [57, 58, 60, 63, 64] work only for RBF networks), I-ELM can work well with a wide type of activation functions no matter whether they are sigmoidal or nonsigmoidal, continuous or noncontinuous, and differentiable or non-differentiable.”
Predicting student academic performance in an engineering dynamics course: A comparison of four types of predictive mathematical models (2013, background): “RBF network is a three-layer feed-forward network that has a good capability to approximate complex nonlinear mapping directly from the input–output data (Huang et al., 2005).”
Quantized Kernel Least Mean Square Algorithm (2012, methodology): “The resource-allocating network (RAN) [10], generalized growing and pruning radial basis function (RBF) networks [11], online kernel-based classifier using adaptive projection algorithms Manuscript received May 1, 2011; revised August 5, 2011; accepted October 9, 2011.”
A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks (2006, methodology): “These include resource allocation network (RAN) [14] and its extensions [15]–[19].”
Selection of Proper Neural Network Sizes and Architectures—A Comparative Study (2012, neutral): “BMLP with three hidden layers.”
An integrated growing-pruning method for feedforward network training (2008, methodology): “[17] have developed an online training algorithm for RBF-based minimal resource allocation networks (MRAN), which uses both growing and pruning.”