Biomedical subjects

A P Braga

Publications and source records attributed to A P Braga.

4 recordsLinked to original sources

PubMed2001

Training SVMs with EDR algorithm.

The aim of this work is to present a new training algorithm for SVMs based on the pattern selection strategy called Error Dependent Repetition (EDR). With EDR, the presentation frequency of a pattern depends on its error: patterns with larger errors are selected more frequently and patterns with smaller error (or learned) are presented with minor frequency. Using a simple iterative process based on gradient ascent, SVM-EDR can solve the dual problem without any assumption about support vectors or the Karush-Kuhn-Tucker (KKT) conditions.

Algorithms↗

PubMed2001

Recent advances in the MOBJ algorithm for training artificial neural networks.

This paper presents a new scheme for training MLPs which employs a relaxation method for multi-objective optimization. The algorithm works by obtaining a reduced set of solutions, from which the one with the best generalization is selected. This approach allows balancing between the training error and norm of network weight vectors, which are the two objective functions of the multi-objective optimization problem. The method is applied to classification and regression problems and compared with Weight Decay (WD), Support Vector Machines (SVMs) and standard Backpropagation (BP). It is shown that the systematic procedure for training proposed results on good generalization neural models, and outperforms traditional methods.

Algorithms↗

PubMed1999

Neural networks learning with sliding mode control: the sliding mode backpropagation algorithm.

Based on the classical backpropagation weight update equations, sliding mode control theory is introduced as a technique to adapt weights of a multi-layer perceptron. As will be demonstrated, the introduction of sliding mode has resulted in a much faster version of the standard backpropagation. The results show also that the proposed algorithm presents some important features of sliding mode control, which are robustness and high speed of learning. In addition to that, this paper shows also how control theory can be applied to train neural networks.

Algorithms↗

PubMedDate not supplied

Inversion of simulated positron annihilation lifetime spectrum using a neural network.

Inversion of positron annihilation lifetime spectroscopy, based on a neural network Hopfield model, is presented in this paper. From a previous reported density function for lysozyme in water a simulated spectrum, without the superposition of statistical fluctuation and spectrometer resolution effects, was generated. These results were taken as the exact results from which the neural network was trained. The precision of the inverted density function was analyzed taking into account the number of neurons and the learning time of the neural network. A fair agreement was obtained when comparing the neural network results with the exact results. For example, the maximum of the density function, with a precision of 0.4% for the percentual relative error, was obtained for 64 neurons.

Journal Article↗