Ensemble competitive learning neural networks with reduced input dimension.

摘要: Conventional neural networks utilize all the dimensions of original input patterns for training and classification. However, a particular attribute does not necessarily contribute to classification may even cause misclassification in certain cases. A new ensemble competitive learning method using reduced dimension is proposed. In contrast previous which adjust parameters, proposed takes advantage information each patterns. Since degree contribution known beforehand, different data sets with one are presented multiple networks. The from network then combined make final decision order improve accuracy, ambiguous output neurons eliminated cannot be assigned any class after training. We use three consensus schemes judge experimental results remote sensing speech indicate improved performance method.