在AdaBoost集成方法的基础上,研究了一种产生式与判别式模型组合的方法。该算法在每轮中同时学习一个产生式分类器和一个判别式分类器,选择误差率较小的作为个体分类器,然后对所有个体分类器采用加权的方法得到最终分类器。实验结果表明,该方法在准确率和收敛速度上都具有很好的效果。 Based on the AdaBoost integration method, a method of combining production and discriminant models is studied. The algorithm learns a production classifier and a discriminant classifier simultaneously in each round, chooses the error rate as the individual classifier, and then uses the weighted method to get the final classifier for all individual classifiers. The experimental results show that this method has a good effect on the accuracy and convergence speed.