In this paper, after analyzing the reasons of poor generalization and overfitting in neural networks, we consider some noise data as a singular value of a continuous function jump discontinuity point. The continuous part can be approximated with the simplest neural networks, which have good generalization performance and optimal network architecture, by traditional algorithms such as constructi...

The two well-known neural network, Hopfield networks and Radial Basis Function networks, have different structures and characteristics. Hopfield neural network and RBF neural network are two of the most commonly-used types of feedback networks and feedforward networks respectively. This study gives an overview for Hopfield neural network and RBF neural network in architectures, the learning pro...

introduction: with using multiple linear regression (mlr), can simultaneously analyses several different variables, but to get the desirable results from the mlr, the samples must be much and accurate. therefore, this method has high sensitivity and may cause errors in results. in addition, to use this method, the variable must have normal distribution and modification follow from a linear rela...

The Hartley transform, a real-valued alternative to the complex Fourier transform, is presented as an efficient tool for the analysis and simulation of earthquake accelerograms. This paper is introduced a novel method based on discrete Hartley transform (DHT) and radial basis function (RBF) neural network for generation of artificial earthquake accelerograms from specific target spectrums. Acce...

According to literature, it is well-known that the training algorithm of RBF neural networks depends a lot by the specific way to obtain the positioning of RBF centers over the input data space, and to fit the neural weights to the output layer, respectively. Having as starting point a real pattern recognition task belonging to video imagery to solve, this paper presents a comparative analysis ...

This paper presents an axiomatic approach for constructing radial basis function (RBF) neural networks. This approach results in a broad variety of admissible RBF models, including those employing Gaussian RBF's. The form of the RBF's is determined by a generator function. New RBF models can be developed according to the proposed approach by selecting generator functions other than exponential ...

It has limitations to apply the traditional mathematical model to assess the risk of the information security for it is characterized by its nonlinearity and uncertainty. The RBF Neural Networks Theory, Particle Swarm Optimization (PSO) Analysis and Fuzzy Evaluation are combined to build a particle swarm optimizing model of Information Security Risk Assessment based on RBF Neural Networks, so a...

This paper presents a novel approach in learning algorithms commonly used for training radial basis function (RBF) neural networks. This approach could be used in applications that need real-time capabilities for retraining RBF neural networks. The proposed method is a Three-Phase Learning Algorithm that optimizes the functionality of the Optimum Steepest Decent (OSD) learning method. RBF neura...

In this paper, a nonlinear offline model of the solid oxide fuel cell (SOFC) is built by using a radial basis function (RBF) neural network based n a genetic algorithm (GA). During the process of modeling, the GA aims to optimize the parameters of RBF neural networks and the optimum alues are regarded as the initial values of the RBF neural network parameters. Furthermore, we utilize the gradie...

Estimate of sediment load is required in a wide spectrum of water resources engineering problems. The nonlinear nature of suspended sediment load series necessitates the utilization of nonlinear methods to simulate the suspended sediment load. In this study Artificial Neural Networks (ANNs) are employed to estimate daily suspended sediment load. Two different ANN algorithms, Multi Layer Perce...