This paper discusses the function approximation properties of the Gelenbe random neural network GNN We use two extensions of the basic model the bipolar GNN BGNN and the clamped GNN CGNN We limit the networks to being feedforward and consider the case where the number of hidden layers does not exceed the number of input layers With these constraints we show that the feedforward CGNN and the BGN...

We propose a novel approximate inference framework that approximates a target distribution by amortising the dynamics of a user-selected Markov chain Monte Carlo (MCMC) sampler. The idea is to initialise MCMC using samples from an approximation network, apply the MCMC operator to improve these samples, and finally use the samples to update the approximation network thereby improving its quality...

In this paper, the application of neural networks for approximating the Neyman-Pearson detector is considered. We propose a strategy to identify the training parameters that can be controlled for reducing the effect of approximation errors over the performance of the neural network based detector. The function approximated by a neural network trained using the mean squared-error criterion is de...

An integrated Neural Network and Gravitational Search Algorithm (HNNGSA) are used to solve Blasius differential equation. To aim this purpose, GSA technique is applied to train a multi-layer perceptron neural network, which is used as approximation solution of the Blasius differential equation. A trial solution of the differential equation is written as sum of two parts. The first part satisfie...

in this study, artificial neural network was used to predict the surface tension of 20 hydrocarbon mixtures. experimental data was divided into two parts (70% for training and 30% for testing). optimal configuration of the network was obtained with minimization of prediction error on testing data. the accuracy of our proposed model was compared with four well-known empirical equations. the arti...

natural fire inflicting irreparable damage to rangelands and forest areas is cause changes in landscape ecology. the purpose of this research is comparison of artificial neural network (ann) and line regression (lr) models to predict of forest and rangelands fires to this end, the data consist fire burned area and fire were used weather data over a period of 7 years (2006-2012(.the result indic...

water quality assessment provides a scientific basis for water resources development and management. this case study proposes a factor analysis- hopfield neural network model (fhnn) based on factor analysis method and hopfield neural network method. the results showed that the factor analysis (fa) technique was introduced to identify important water quality parameters. results revealed that bio...

Combining neural network with evolutionary algorithms leads to evolutionary artificial neural network. Evolutionary algorithms like GA to train neural nets choose their structure or design related aspects like the functions of their neurons. Along basic concepts of neural networks and genetic algorithm this paper includes a flexible method for solving travelling salesman problem using genetic a...

production of highly viscous tar sand bitumen using steam assisted gravity drainage (sagd) with a pair of horizontal wells has advantages over conventional steam flooding. this paper explores the use of artificial neural networks (anns) as an alternative to the traditional sagd simulation approach. feed forward, multi-layered neural network meta-models are trained through the back-error-propaga...

A new autopilot design for bank-to-turn (BTT) missiles is presented. In the design of autopilot, a ridge Gaussian neural network with local learning capability and fewer tuning parameters than Gaussian neural networks is proposed to model the controlled nonlinear systems. We prove that the proposed ridge Gaussian neural network, which can be a universal approximator, equals the expansions of ro...