SciELO - Scientific Electronic Library Online

 
vol.19 issue2Characterization of Difficult Bin Packing Problem Instances Oriented to Improve Metaheuristic AlgorithmsEvolutionary Multi-objective Optimization for Scheduling Professor Evaluations in Cuban Higher Education author indexsubject indexsearch form
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • Have no similar articlesSimilars in SciELO

Share


Computación y Sistemas

Print version ISSN 1405-5546

Abstract

COELLO, Lenniet; FERNANDEZ, Yumilka; FILIBERTO, Yaima  and  BELLO, Rafael. Improving the Multilayer Perceptron Learning by Using a Method to Calculate the Initial Weights with the Similarity Quality Measure Based on Fuzzy Sets and Particle Swarms. Comp. y Sist. [online]. 2015, vol.19, n.2, pp.309-320. ISSN 1405-5546.  http://dx.doi.org/10.13053/CyS-19-2-2202.

The most widely used neural network model is Multilayer Perceptron (MLP), in which training of the connection weights is normally completed by a Back Propagation learning algorithm. Good initial values of weights bear a fast convergence and a better generalization capability even with simple gradient-based error minimization techniques. This work presents a method to calculate the initial weights in order to train the Multilayer Perceptron Model. The method named PSO+RST+FUZZY is based on the similarity quality measure proposed within the framework of the extended Rough Set Theory that employs fuzzy sets to characterize the domain of similarity thresholds. Sensitivity of BP to initial weights with PSO+RST+FUZZY was studied experimentally, showing better performance than other methods used to calculate feature weights.

Keywords : Multilayer perceptron; weight initialization; similarity quality measure; fuzzy sets.

        · text in English     · English ( pdf )

 

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License