Selecting Variables for Neural Network Committees
The aim of the variable selection is threefold: to reduce model complexity, to promote diversity of committee networks, and to find a trade-off between the accuracy and diversity of the networks. To achieve the goal, the steps of neural network training, aggregation, and elimination of irrelevant input variables are integrated based on the negative correlation learning  error function. Experimental tests performed on three real world problems have shown that statistically significant improvements in classification performance can be achieved from neural network committees trained according to the technique proposed.
KeywordsCommittee Member Neural Network Training Pattern Recognition Letter Negative Correlation Learn Pima Indian Diabetes
Unable to display preview. Download preview PDF.