In this paper, learning algorithms for radial basis function (RBF) networks are discussed. Whereas multilayer perceptrons (MLP) are typically trained with backpropagation algorithms, starting the training procedure with a random initialization of the MLP's parameters, an RBF network may be trained in many different ways. We categorize these RBF training methods into one-, two-, and three-phase ...

We present a novel numerical method for solving ordinary differential equations using radial basis function (RBF) network with extreme learning machine algorithm. A single-layer RBF link neural model has been developed the proposed method. The weight from hidden layer to output can be calculated efficiently by experimental comparison of various methods proves that shows better performance than ...

We present a generalization of the RBF-FD method that allows full control of the overlap between RBF-FD stencils. We accomplish this by introducing a continuous overlap parameter δ ∈ [0, 1] such that δ = 1 recovers the standard RBF-FD method and δ = 0 results in a full decoupling of the RBF-FD stencils. We show with a simple example that global interpolation with both RBFs and RBFs augmented wi...

In this study, a reliability-based RBF neural network ensemble forecasting model is proposed to overcome the shortcomings of the existing neural ensemble methods and ameliorate forecasting performance. In this model, the ensemble weights are determined by the reliability measure of RBF network output. For testing purposes, we compare the new ensemble model’s performance with some existing netwo...

In this paper, evolutionary multi-objective selection method of RBF networks structure is considered. The candidates of RBF network structure are encoded into the chromosomes in GAs. Then, they evolve toward Pareto-optimal front defined by several objective functions concerning with model accuracy and model complexity. An ensemble network constructed by such Pareto-optimal models is also consid...

A neural network-based model reference adaptive control approach (MRAC) for ship steering systems is proposed in this paper. For the nonlinearities of ship steering system, performances of traditional adaptive control algorithms are not satisfactory in fact. The presented MRAC system utilizes RBF neural network to approximate the unknown nonlinearities in order to get a high adaptive control pe...

In this work the mathematical model of a spatial pattern in chemical and biological systems is investigated numerically. The proposed model considered as a nonlinear reaction-diffusion equation. A computational approach based on finite difference and RBF-collocation methods is conducted to solve the equation with respect to the appropriate initial and boundary conditions. The ability and robust...

Air-pressure limit value is an important conditional parameter of artificial respiration. The pulmonary characteristics are very different according to the person. For setting appropriate ventilation conditions fitting to each patient, it is necessary to establish a mathematical model describing the mechanism of human respiratory system, and to know the pulmonary characteristic of each patient ...

The current fault diagnosis methods based on conventional BP neural network and RBF neural network exist long training time, slow convergence speed and low judgment accuracy rate and so on. In order to improve the ability of fault diagnosis, this paper puts forward a kind of fault diagnosis method based on RBF Neural Network improved by PSO algorithm. By using particle swarm algorithm’s heurist...