为了提升视条件而定的深度卷积网络(conditional deep learning network,CDLN)的分类准确率,提出一种多分类器联合训练的方法.在训练网络时将多个分类器的输出误差同时进行反向传播,以校正网络权重.以Le Net-5、Alex Net为基础构造神经网络CDLN-L和CDLN-A,以MNIST、CIFAR-100和Pascal Voc数据集为实验样本进行实验,网络的分类准确率均得到提升,最高提升了4.39%.实验表明,提出的联合训练方法能够提升CDLN的分类准确率.
【英文摘要】
To improve the classification accuracy of convolution neural network similar to conditional deep learning network( CDLN),a method of joint training with multiple classifiers was proposed in this paper.When training the network,all the error signals of the classifiers were applied to update weights by Back Propagation. In the experiments,CDLN-L and CDLN-A based on Le Net-5 and Alex Net were studied on the MINIST,CIFAR-100 and Pascal Voc databases,and an increase of 4. 39% in classification accuracy was achie...
| 
推荐 
点击下列相关研究机构和相关文献作者，可以直接查到这些机构和作者被《中国知识资源总库》收录的其它文献，使您全面了解该机构和该作者的研究动态和历史。
