The experiments on UCI Machine Learning Repository prove that, compared to existing measures, EPD shows stronger ability in predicting the performance of multiple classifier systems.

对UCI机器学习数据库的实验证明，相对于其它方法，EPD方法对多分类器系统性能的预测能力更强。

youdao

Experiment shows neural network classifier that is optimized by algorithm could not only have fast learning speed but also ensure accuracy of classification.

实验结果表明：算法优化后的神经网络分类器不但学习速度快，还能保证分类精度。

youdao

Learning rules are constructed according to deterministic annealing to optimize classifier parameters, on purpose to reduce classification error and system entropy of the space to be identified.

由确定性退火技术构造学习规则用于优化分类器参数，目的是减少分类误差以及待识别空间的系统熵。

youdao