University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Neural network regularization and ensembling using multi-objective evolutionary algorithms

Jin, Y, Okabe, T and Sendhoff, B (2004) Neural network regularization and ensembling using multi-objective evolutionary algorithms In: Congress on Evolutionary Computation, 2004-06-19 - ?.

[img]
Preview
PDF
jin04a.pdf
Available under License : See the attached licence file.

Download (1899Kb)
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf

Download (32Kb)

Abstract

Regularization is an essential technique to improve generalization of neural networks. Traditionally, regularization is conduced by including an additional term in the cost function of a learning algorithm. One main drawback of these regularization techniques is that a hyperparameter that determines to which extension the regularization influences the learning algorithm must be determined beforehand. This paper addresses the neural network regularization problem from a multi-objective optimization point of view. During the optimization, both structure and parameters of the neural network will be optimized. A slightly modified version of two multi-objective optimization algorithms, the dynamic weighted aggregation (DWA) method and the elitist non-dominated sorting genetic algorithm (NSGA-II) are used and compared. An evolutionary multi-objective approach to neural network regularization has a number of advantages compared to the traditional methods. First, a number of models with a spectrum of model complexity can be obtained in one optimization run instead of only one single solution. Second, an efficient new regularization term can be introduced, which is not applicable to gradient-based learning algorithms. As a natural by-product of the multi-objective optimization approach to neural network regularization, neural network ensembles can be easily constructed using the obtained networks with different levels of model complexity. Thus, the model complexity of the ensemble can be adjusted by adjusting the weight of each member network in the ensemble. Simulations are carried out on a test function to illustrate the feasibility of the proposed ideas.

Item Type: Conference or Workshop Item (Paper)
Additional Information: © 2004 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Divisions: Faculty of Engineering and Physical Sciences > Computing Science
Depositing User: Symplectic Elements
Date Deposited: 20 Jul 2012 13:11
Last Modified: 23 Sep 2013 19:27
URI: http://epubs.surrey.ac.uk/id/eprint/532846

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800