Neural network training
作者： John Carney
DOI:
关键词:
摘要: A prediction model is generated by training an ensemble of multiple neural networks, and estimating the performance error ensemble. In a subsequent stage trained using adapted set so that preceding bias component modelled compensated for in new each successive compared with all ensembles combined. No further stages take place when there no improvement error. Within stage, optimum number iterative weight updates determined, variance minimised.
lens.org 参考文章(5)
William P. Lincoln, Clustered neural networks ,(1990)
Laurence F. Wood, Neural network training tool ,(1988)
JONGWAN KIM, JESUNG AHN, SEONGWON CHO, Ensemble competitive learning neural networks with reduced input dimension. International Journal of Neural Systems. ,vol. 6, pp. 133- 142 ,(1995) , 10.1142/S0129065795000111
J.G. Carney, P. Cunningham, U. Bhagwan, Confidence and prediction intervals for neural network ensembles international joint conference on neural network. ,vol. 2, pp. 1215- 1218 ,(1999) , 10.1109/IJCNN.1999.831133
Y. Shimshoni, N. Intrator, Classification of seismic waveforms by integrating ensembles of neural networks Proceedings of International Workshop on Neural Networks for Identification, Control, Robotics and Signal/Image Processing. pp. 368- 376 ,(1996) , 10.1109/NNSP.1996.548375