Evolutionary product unit based neural networks for regression
Neural Networks
Modelling of a magneto-rheological damper by evolving radial basis function networks
Engineering Applications of Artificial Intelligence
Frontiers of Computer Science in China
Construction cosine radial basic function neural networks based on artificial immune networks
ADMA'10 Proceedings of the 6th international conference on Advanced data mining and applications - Volume Part II
Hybrid artificial neural networks: models, algorithms and data
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part II
Hybrid neural network model based on multi-layer perceptron and adaptive resonance theory
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Neuron selection for RBF neural network classifier based on multiple granularities immune network
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part II
An adaptive classifier based on artificial immune network
LSMS'07 Proceedings of the 2007 international conference on Life System Modeling and Simulation
Hi-index | 0.00 |
Radial basis function (RBF) networks are widely used for modeling a function from given input-output patterns. However, two difficulties are involved with traditional RBF (TRBF) networks: The initial configuration of an RBF network needs to be determined by a trial-and-error method, and the performance suffers when the desired output has abrupt changes or constant values in certain intervals. We propose a novel approach to over. come these difficulties. New kernel functions are used for hidden nodes, and the number of nodes is determined automatically by an adaptive resonance theory (ART)-like algorithm. Parameters and weights are initialized appropriately, and then tuned and adjusted by the gradient-descent method to improve the performance of the network. Experimental results have shown that the RBF networks constructed by our method have a smaller number of nodes, a faster learning speed, and a smaller approximation error than the networks produced by other methods.