Artificial neural networks are computer algorithms that simulate, in a very simplified form, the ability of brain neurons to process information. Basically, within each unit of the network, all the input weighted signals are summed and an excitatory or inhibitory signal is then fired to the next layer's units (Fig. 1). The training of the neural net is performed by adjusting the weights between...

In this paper, a new method for estimation of transient parameters of transformer high voltage winding using the artificial neural networks (ANN) is proposed. An ANN with different structures is trained for parameters estimation of transformer winding Detailed Model that data is generated by analysis of frequency response. It is shown that feed-forward back propagation network with Levenberg-Ma...

—The biggest challenge in the field of image processing is to recognize documents both in printed and handwritten format. Optical Character Recognition (OCR) is a type of document image analysis where scanned digital image that contains either machine printed or handwritten script input into an OCR software engine and translating it into an editable machine readable digital text format. A Neura...

We propose a general class of multilayer feed-forward neural networks where the combination of inputs in every node is formed by hybrid linear and nonlinear (of the morphological/rank type) operations. We demonstrate that this structure ooers eecient solutions to pattern classiication problems by requiring fewer nodes or fewer parameters to estimate than those needed by multilayer perceptrons. ...

This report presents the use of feed forward ANNs with accelerated Back propagation and Support Vector Regression to predict the joint angles of walking cats using the EMG signals obtained from several muscles of the cat hind and fore limbs. The MATLAB software was used with NN and SVM tools. The results have demonstrated that, both methods can be effectively used to predict the joint angles, i...

In this paper, an online isolated Arabic handwritten character recognition system is introduced. The system can be adapted to achieve the demands of hand-held and digital tablet applications. To achieve this goal, despite of single neural networks, four neural networks are used, one for each cluster of characters. Feed forward back propagation neural networks are used in classification process....

In this paper Discrete wavelet Transform with logarithmic Power Spectrum Density (PSD) are combined for speaker formants extraction, to be used as evident classification features. For classification, Feed Forward Back Propagation Neural Network FFBNN method is proposed. The Discrete Wavelet formants Neural Network DWFNNT system works with excellent capability of features tracking even with 0dB ...

The aim of this paper is to implement a Multilayer Perceptron (MLP) Neural Network to recognize and predict handwritten digits from 0 to 9. A dataset of 5000 samples were obtained from MNIST. The dataset was trained using gradient descent back-propagation algorithm and further tested using the feed-forward algorithm. The system performance is observed by varying the number of hidden units and t...

In this paper, we propose different strategies for simplifying filters, used as feature extractors, to be learnt in convolutional neural networks (ConvNets) in order to modify the hypothesis space, and to speed-up learning and processing times. We study two kinds of filters that are known to be computationally efficient in feed-forward processing: fused convolution/sub-sampling filters, and sep...

Complex networks, like the scale-free model, are observed in many biological and social systems and the application of this topology to artificial neural networks (ANN) leads to interesting considerations. In this paper, we present a preliminary study on the modelling capabilities of ANN with complex topologies. We used an evolutionary algorithm (EA) to train them providing thus the paradigm of...