Please use this identifier to cite or link to this item:
Title: Complementary neural networks for regression problems
Authors: Somkid Amornsamankul
Keywords: Bench-mark problems;complementary neural networks;Complementary output;Concrete compressive strength;Prediction performance;Regression problem
Issue Date: 2009
Publisher: Proceedings of the 2009 International Conference on Machine Learning and Cybernetics
Citation: 2009 International Conference on Machine Learning and Cybernetics
Abstract: In this paper, complementary neural networks (CMTNN) are used to solve the regression problem. CMTNN consist of a pair of opposite neural networks. The first neural network is trained to predict degree of truth values and the second neural network is trained to predict degree of falsity values. Both neural networks are complementary to each other since they deal with pairs of complementary output values. In order to predict the more accurate outputs, each pair of the truth and falsity values are aggregated based on two techniques which are equal weight combination and dynamic weight combination. The first technique is just a simple averaging whereas the second technique deals with errors occurred in the prediction. We experiment our approach to the classical benchmark problems including housing, concrete compressive strength, and computer hardware from the UCI machine learning repository. It is found that complementary neural networks improve the prediction performance as compared to the traditional single backpropagation neural network and support vector regression used to predict only truth values. Furthermore, the difference between the predicted truth value and the complement of the predicted falsity value can be used as an uncertainty indicator to support the confidence in the prediction of unknown input data.
ISSN: 978-142443703-0
Appears in Collections:Mathematics: International Proceedings

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.