Improving the Multilayer Perceptron Learning by using a Method to Calculate the Initial Weights with the Quality of Similarity Measure based on Fuzzy Sets and Particle Swarms

Authors

  • Lenniet Coello Universidad de Camagüey
  • Yumilka Fernandez Universidad de Camagüey
  • Yaima Filiberto Universidad de Camagüey
  • Rafael Bello Universidad Central de Las Villas

DOI:

https://doi.org/10.13053/cys-19-2-2202

Keywords:

Multilayer perceptron, weight initialization, quality of similarity Measure, fuzzy sets.

Abstract

The most widely used neural network model is the Multilayer Perceptron (MLP), in which the connection weights training are normally completed by a Back Propagation learning algorithm. The 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 quality of similarity measure proposed on the framework of the extended Rough Set Theory that employs fuzzy sets to characterize the domain of the similarity thresholds. Sensitivity of BP to initial weights with PSO+RST+FUZZY was studied experimentally, and shows a better performance than other methods used to calculate the weight of the feature.

Author Biographies

Lenniet Coello, Universidad de Camagüey

She is a professor at the Faculty of Computer Sciences, University of Camagüey. She graduated of Computer Sciences in 2011 at the University of Camagüey. She received her M.Sc. in mathematics teaching in 2014. She has participated in 15 congresses, most of them international and of high scientific level. She has 7 scientific publications, most of them in Referenced Data Bases. She has participated in many researches of great impact and with significant results. She teaches Artificial Intelligence, Knowledge Based Systems and Data Mining. She is a member of the Research Group on Artificial Intelligence.

Yumilka Fernandez, Universidad de Camagüey

Yumilka B. Fernández. Received her Bachelor degree in Computer Science Engineer in 2004 at Universidad de Camagüey(UC),Cuba and MSc. in Applied Computer Science in 2006 at Universidad Central de Las Villas (UCLV), Cuba. Her scientific interest is in the Artificial intelligence discipline, particularly Machine learning, Soft computing, and Decision making. She has participated in Congress international and with high scientific level. She is a member of the Research Group on Artificial Intelligence.

Yaima Filiberto, Universidad de Camagüey

Yaima Filiberto. Received her Bachelor degree in Computer Science Engineer in 2006 and MSc. in Applied Computer Science in 2008 both at Universidad de Camagüey (UC), Cuba and his PhD degree in 2012 at Universidad Central de Las Villas (UCLV), Cuba. His scientific interest is in the Artificial intelligence discipline, particularly Machine learning, Soft computing, KDD and Decision making. He has published about of 30 scientific works. She is a Director of the Science and Technic in UC.

Rafael Bello, Universidad Central de Las Villas

Rafael Bello. Received his Bachelor degree in Cybernetic and Mathematics at Universidad Central de Las Villas (UCLV), Cuba, in 1982, and his PhD degree in 1987. His scientific interest is in the Artificial intelligence discipline, particularly Metaheuristics, Softcomputing, Machine learning, and Decision making. He has published about of 200 scientific works. He is a Member of the Cuban Science Academy and the Director of the Center of Studies on Informatics at UCLV.

Downloads

Published

2015-06-01

Issue

Vol. 19 No. 2 (2015): 19(2) April-June 2015

Section

Articles

License 

Hereby I transfer exclusively to the Journal "Computación y 
Sistemas", published by the Computing Research Center (CIC-IPN),
the Copyright of the aforementioned paper. I also accept that these 
rights will not be transferred to any other publication, in any other 
format, language or other existing means of developing.
I certify that the paper has not been previously disclosed or simultaneo
usly submitted to any other publication, and that it does not contain 
material whose publication would violate the Copyright or other 
proprietary rights of any person, company or institution. I certify that 
I have the permission from the institution or company where I work or 
study to publish this work.
The representative author accepts the responsibility for the publication
of this paper on behalf of each and every one of the authors. 
This transfer is subject to the following conditions:
  • The authors retain all ownership rights (such as patent rights) of this work, except for the publishing rights transferred to the CIC, through this document.
  • Authors retain the right to publish the work in whole or in part in any book they are the authors or publishers. They can also make use of this work in conferences, courses, personal web pages, and so on.
  • Authors may include working as part of his thesis, for non-profit distribution only.