eprintid: 3294 rev_number: 2 eprint_status: archive userid: 1 dir: disk0/00/00/32/94 datestamp: 2023-11-09 15:51:33 lastmod: 2023-11-09 15:51:33 status_changed: 2023-11-09 15:46:30 type: conference_item metadata_visibility: show creators_name: Hassan, S. creators_name: Khosravi, A. creators_name: Jaafar, J. title: Variance-covariance based weighing for neural network ensembles ispublished: pub keywords: Artificial intelligence techniques; Forecast combinations; Forecasting accuracy; Load demand; Neural network (nn); Neural network ensembles; Variance-covariance; Weighted averaging, Cybernetics; Electric network topology; Experiments; Neural networks, Forecasting note: cited By 1; Conference of 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 ; Conference Date: 13 October 2013 Through 16 October 2013; Conference Code:102429 abstract: Neural network (NN) is a popular artificial intelligence technique for solving complicated problems due to their inherent capabilities. However generalization in NN can be harmed by a number of factors including parameter's initialization, inappropriate network topology and setting parameters of the training process itself. Forecast combinations of NN models have the potential for improved generalization and lower training time. A weighted averaging based on Variance-Covariance method that assigns greater weight to the forecasts producing lower error, instead of equal weights is practiced in this paper. While implementing the method, combination of forecasts is done with all candidate models in one experiment and with the best selected models in another experiment. It is observed during the empirical analysis that forecasting accuracy is improved by combining the best individual NN models. Another finding of this study is that reducing the number of NN models increases the diversity and, hence, accuracy. © 2013 IEEE. date: 2013 official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84893616999&doi=10.1109%2fSMC.2013.548&partnerID=40&md5=aa07a4a882d3d2060e6e4f3b254b3dbb id_number: 10.1109/SMC.2013.548 full_text_status: none publication: Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013 place_of_pub: Manchester pagerange: 3214-3219 refereed: TRUE isbn: 9780769551548 citation: Hassan, S. and Khosravi, A. and Jaafar, J. (2013) Variance-covariance based weighing for neural network ensembles. In: UNSPECIFIED.