Due to the chaotic nature of multilayer perceptron training, training error usually fails to be a monotonically nonincreasing function of the number of hidden units. New training algorithms are developed where weights and thresholds from a well-trained smaller network are used to initialize a larger network. Methods are also developed to reduce the total amount of training required. It is shown...

This paper investigates the possibility of describing vowels phonetically using an automated method. Models of the phonetic dimensions of the vowel space are built using two multi-layer perceptrons trained using eight cardinal vowels. The paper aims to improve the positioning of vowels in the open-close dimension by experimenting with a parameter in the model which is the parameter which contro...

Three-phase induction motor are one of the most important elements of electromechanical energy conversion in the production process. However, they are subject to inherent faults or failures under operating conditions. The purpose of this paper is to present a comparative study among intelligent tools to classify short-circuit faults in stator windings of induction motors operating with three di...

Neural computation in Clifford algebras, which include familiar complex numbers and quaternions as special cases, has recently become an active research field. As always, neurons are the atoms of computation. The paper provides a general notion for the Hessian matrix of Clifford neurons of an arbitrary algebra. This new result on the dynamics of Clifford neurons then allows the computation of o...

Backpropagation is one of the most famous training algorithms for multilayer perceptrons. Unfortunately it can be very slow for practical applications. Over the last years many improvement strategies have been developed to speed up backpropagation. It’s very difficult to compare these different techniques, because most of them have been tested on various specific data sets. Most of the reported...

In this paper we e v aluate the performance of Support Vector Machines SVMs and Multi-Layer Perceptrons MLPs on two diierent problems of Particle Identiication in High Energy Physics experiments. The obtained results indicate that SVMs and MLPs tend to perform very similarly.

In this paper, a simple, general method of adding auxiliary stochastic neurons to a multi-layer perceptron is proposed. It is shown that the proposed method is a generalization of recently successful methods of dropout [5], explicit noise injection [12,3] and semantic hashing [10]. Under the proposed framework, an extension of dropout which allows using separate dropping probabilities for diffe...

We present a training method which adjusts the weights of the MLP (Multilayer Perceptron) to preserve the distance invariance in a low dimensional space. We apply visualization techniques to display the detailed representations of the trained neurons.

The paper presents a method for automatic detection and monitoring of small waterlogged areas in farmland, using multispectral satellite images and neural network classifiers. In the waterlogged areas, excess water significantly damages or completely destroys the plants, thus reducing the average crop yield. Automatic detection of (waterlogged) crops damaged by rising underground water is an im...