One method proposed for improving the generalization capability of a feedforward network trained with the backpropagation algorithm is to use artificial training vectors which are obtained by adding noise to the original training vectors. We discuss the connection of such backpropagation training with noise to kernel density and kernel regression estimation. We compare by simulated examples (1)...

Text classification gains lot of significance in the current scenario of processing and retrieval of text. Several algorithms are suggested for the text classification problem. This paper provides the solution by Back propagation network. The backpropagation network algorithm is adapted for the text classification. Before providing the algorithm the techniques used for feature identification is...

In this paper, we explore the parallel implementation of the backpropagation algorithm with and without hidden layers on MasPar MP-1. This implementation is based on a SIMD architecture, and uses a backpropagation model. Our implementation uses weight batching versus on-line updating of the weights which is used by most serial and parallel implementations of backpropagation. This method results...

In this paper the Sigma-if artificial neural network model is considered, which is a generalization of an MLP network with sigmoidal neurons. It was found to be a potentially universal tool for automatic creation of distributed classification and selective attention systems. To overcome the high nonlinearity of the aggregation function of Sigma-if neurons, the training process of the Sigma-if n...

Heat transfer fluids have inherently low thermal conductivity that greatly limits the heat exchange efficiency. While the effectiveness of extending surfaces and redesigning heat exchange equipments to increase the heat transfer rate has reached a limit, many research activities have been carried out attempting to improve the thermal transport properties of the fluids by adding more thermally c...

In this study, an artificial neural network was used to predict the minimum force required to single point incremental forming (SPIF) of thin sheets of Aluminium AA3003-O and calamine brass Cu67Zn33 alloy. Accordingly, the parameters for processing, i.e., step depth, the feed rate of the tool, spindle speed, wall angle, thickness of metal sheets and type of material were selected as input and t...

Proposes a neural network based invariant character recognition system using double backpropagation network. The model consists of two parts. The first is a preprocessor which is intended to produce a translation, rotation and scale invariant representation of the input pattern. The second is a neural net classifier. The outputs produced by the preprocessor at the first stage are classified by ...

Backpropagation and contrastive Hebbian learning are two methods of training networks with hidden neurons. Backpropagation computes an error signal for the output neurons and spreads it over the hidden neurons. Contrastive Hebbian learning involves clamping the output neurons at desired values and letting the effect spread through feedback connections over the entire network. To investigate the...