竞争监督学习法在集成型识别系统中的应用

COMPETITIVE SUPERVISED LEARNING ALGORITHM AND APPLICATION IN INTEGRATED RECOGNITION SYSTEM

在集成方法中，神经网络集成方法对研制集成型模式识别系统是有效的．但是，单个子分类器和集成网络的性能对集成系统的整体识别效果都有影响．因此，要进一步提高系统性能也必须改进子分类器和集成网络．文中采用竞争监督学习法，构造一个网络集成系统，用于手写数字字符识别．实验证明，该方法的确能够改进系统的收敛速度和泛化能力．

In pattern recognition application,integration of artificial neural networks has been recognized as a powerful tool,but the performance of the sub classifiers has effect on the performance of the whole integration system.In this paper,we apply the proposed algorithm Competitive Supervised Learning Algorithm to the integrated recognition neural network system. Experimental results have confirmed that the proposed algorithm improves lear ning and generalization of the system.