In this paper,the sparse autoencoders(Sparse Autoencoder,SAE) model is applied to the digital recognition,and a deep network is constructed by stacking a plurality of sparse autoencoders,using Greedy Layer-Wise Unsupervised Learning algorithm to initialize the weights of the network and back propagation algorithm to optimize the parameters of the network. The stacked sparse autoencoders are used to learn the features of the digital image,and the softmax classifier is used to conduct the digital classificati...
| 
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。
