This work concerns the estimation of multidimensional nonlinear regression models using multilayer perceptrons (MLPs). The main problem with such models is that we need to know the covariance matrix of the noise to get an optimal estimator. However, we show in this paper that if we choose as the cost function the logarithm of the determinant of the empirical error covariance matrix, then we get...

We consider nonlinear quantile regression involving multilayer perceptrons (MLP). In this paper we investigate the asymptotic behavior of quantile regression in a general framework. First by allowing possibly non-identifiable regression models like MLP's with redundant hidden units, then by relaxing the conditions on the density of the noise. In this paper, we present an universal bound for the...

In many technical issues, the processes of interest could be precisely modelled if only all the relevant information were available. On the other hand, detailed modelling is frequently not feasible due to the cost of acquiring appropriate data. The paper discusses the way self-organising maps and multilayer perceptrons can be used to develop two-stage algorithm for autonomous construction of pr...

A large fraction of recent work in artificial neural nets uses multilayer perceptrons trained with the back-propagation algorithm described by Rumelhart et. a1. This algorithm converges slowly for large or complex problems such as speech recognition, where thousands of iterations may be needed for convergence even with small data sets. In this paper, we show that training multilayer perceptrons...

Training a multilayer perceptron by an error backpropagation algorithm is slow and uncertain. This paper describes a new approach which is much faster and certain than error backpropagation. The proposed approach is based on combined iterative and direct solution methods. In this approach, we use an inverse transformation for linearization of nonlinear output activation functions, direct soluti...

A study is presented to compare the performance of multilayer perceptrons, radial basis function networks, and probabilistic neural networks for classification. In many classification problems, probabilistic neural networks have outperformed other neural classifiers. Unfortunately, with this kind of networks, the number of required operations to classify one pattern directly depends on the numb...

Here the authors propose the use of Fuzzy Multilayer Perceptrons for classification of land use and land cover patterns in the Brazilian Amazon, using time series of vegetation index, taken from NASA’s MODIS (Moderate Resolution Imaging Spectroradiometer) sensor. In addition to the traditional Multilayer Perceptron (MLP), three fuzzy implementations were investigated. These methods were applied...

Multilayer perceptrons and radial basis function networks are used most often in classification tasks, even though the two neural networks have different performance in classification tasks depending on the available training data sets. This paper shows the accuracy change in classification of the two neural networks when training data set size changes. Experiments were run with four data sets ...

It’s well known that the computing time to train multilayer perceptrons is very long because of weight space of the neural networks and small amount of adjustment of the wiights for convergence. The matter becomes worse when the size of training data set is large, which is common in data mining tasks. Moreover, depending on samples, the performance of neural networks change. So, in order to det...