Metaheuristic algorithm to train product and sigmoid neural network classifiers

Abstract

This paper develops three frameworks based on a metaheuristic algorithm to train neural network classifiers. The architecture is a single‐hidden‐layer feedforward network. The first methodology spreads a base configuration over the nodes of a computing cluster; each of them executes the same algorithm to train the neural network with a different parameter setting. The second approach does a refined training via a biphase metaheuristic algorithm to maintain the diversity a period longer than the usual; it may be run in a sequential or distributed way. The third framework performs a data preparation phase by means of feature subset selection to reduce the number of inputs to the biphase metaheuristic algorithm. The two first methodologies have been tested using a complete test bed with product and unipolar sigmoid units in the hidden layer, and the statistical tests reveal that product nodes are significantly the most accurate. The third framework has included four feature subset selectors with different properties to reduce the number of inputs to the product unit artificial neural network, and the nonstatistical test shed light on that the results with a preprocessing phase are significantly more accurate than the results with the raw data.

A Methodology for Calculating Greenhouse Effect of Aircraft Cruise Using Genetic Algorithm-Optimized Wavelet Neural Network

“…Network. e gradient learning method presented above enables the network to gradually adjust along the direction of local improvement, which means inappropriate initial weights and factors can increase the possibility of falling into local optimum or even failing because of the complexity and nondifferentiability of the search space [25]. In this regard, the genetic algorithm (GA) with global search capability is employed to improve the model by optimizing the initial weights and factors in this paper.…”

Aproximación a una metodología de análisis de las emociones en el discurso político televisado

“…La primera vía sienta sus bases en que los usuarios de tecnologías dejan un rastro en la red en forma de datos, lo que permite hacer retratos gracias a algoritmos que originan unos patrones. Los macrodatos o Big data capacitan la visualización, recuperación y gestión de grandes volúmenes de datos aplicando la minería de datos u obtención de modelos de predicción como los árboles de decisión o las redes neuronales artificiales, que son entrenadas con el fin de construir un modelo que reproduce el método de aprendizaje del cerebro humano y realiza predicciones mediante algoritmos de patrones de comportamiento y acción (Tallón-Ballesteros, 2019). Esto permite controlar el itinerario de un usuario y parametrizar las emociones o la empatía que produce un producto o una idea en la red.…”