• Jun 14, 2017 News!Vol.6, No.3 has been indexed by EI(Inspec)!   [Click]
  • May 03, 2016 News!Vol.5, No.5 has been indexed by EI(Inspec)!   [Click]
  • May 03, 2016 News!Vol.5, No.4 has been indexed by EI(Inspec)!   [Click]
General Information
    • ISSN: 2010-3700
    • Frequency: Bimonthly
    • DOI: 10.18178/IJMLC
    • Editor-in-Chief: Dr. Lin Huang
    • Executive Editor:  Ms. Cherry L. Chen
    • Abstracing/Indexing: Engineering & Technology Digital Library, Google Scholar, Crossref, ProQuest, Electronic Journals Library, DOAJ and EI (INSPEC, IET).
    • E-mail: ijmlc@ejournal.net
Editor-in-chief
Dr. Lin Huang
Metropolitan State University of Denver, USA
It's my honor to take on the position of editor in chief of IJMLC. We encourage authors to submit papers concerning any branch of machine learning and computing.
IJMLC 2012 Vol.2(3): 283-286 ISSN: 2010-3700
DOI: 10.7763/IJMLC.2012.V2.131

Adaptive Ensemble Construction based on Progressive Interactive Training of Neural Networks

M. A. H. Akhand and K. Murase

Abstract—The goal of an ensemble construction with several neural networks (NNs) is to achieve better generalization ability over a single neural network. In a Neural Network Ensemble (NNE), component networks solve the desired problem independently and combine their outputs for NNE’s output. Therefore, the size of an NNE plays an important role in determining the performance for a particular problem. Although there has been much work for constructing ensembles, most of the works trains predefined number of NNs for an NNE. This study presents a problem dependent adaptive NNE construction method based on Progressive Interactive Training Scheme (PITS) of NNs. In PITS, a predefined number of NNs are trained one by one in a progressive manner, where each NN is concerned with a specific task that has not been solved by any previously trained NN. Proposed Adaptive PITS (APITS) is an extension of PITS utilizing inherited benefit of its sequential style training. APITS employs a simple overhead in PITS while training NNs one after another sequentially. The overhead determines more NNs training will be beneficial or not for a given problem and therefore, return different number of NNs for different problems. The proposed method has been evaluated on several benchmark problems, and the method (with concise NNE) is shown competitive generalization ability with the popular NNE methods.

Index Terms—Generalization, neural network ensemble, problem dependent adaptive ensemble.

M. A. H. Akhand is with the Dept. of Computer Science and Engineering, Khulna University of Engineering and Technology, Khulna-9203, Bangladesh (e-mail: akhand@cse.kuet.ac.bd).
K. Murase is Graduate School of Engineering, University of Fukui, 3-9-1 Bunkyo, Fukui 910-8507, Japan (e-mail: murase@.u-fukui.ac.jp).

[PDF]

Cite: M. A. H. Akhand and K. Murase, "Adaptive Ensemble Construction based on Progressive Interactive Training of Neural Networks," International Journal of Machine Learning and Computing vol. 2, no. 3, pp. 283-286, 2012.

Copyright © 2008-2015. International Journal of Machine Learning and Computing. All rights reserved.
E-mail: ijmlc@ejournal.net