稀疏和标签约束半监督自动编码机的分类算法

自动编码机通过深度无监督学习能够表达数据的语义特征，但由于其隐含层节点个数难以有效确定，所处理的数据进一步用于分类时常会导致分类准确度低、稳定性弱等问题。针对这些问题，提出了一种稀疏和标签约束的半监督自动编码机（SLRAE），以实现无监督学习与监督学习的有机结合，更准确地抽取样本的本质特征。稀疏约束项针对每个隐含节点的响应添加约束条件，从而在隐含神经元数量较多的情况下仍可发现数据中潜在的结构；同时引入标签约束项，以监督学习的方式比对实际标签与期望标签，针对性地调整网络参数，进一步提高分类准确率。为验证所提方法的有效性，实验中对多个数据集进行广泛地测试，其结果表明，相对传统自动编码机（AE）、稀疏自动机（SAE）以及极限学习机（ELM），SLRAE所处理的数据应用于同一分类器，能明显提高分类准确率和稳定性。

Semi-supervised auto-encoder using sparse and label regularizations for classification

Auto-Encoder could express the semantic features of data through deep unsupervised learning, but it was hard to determine the nodes of hidden layer and the processing of data for classification often leads to low accuracy and low stability. To solve the problems, this paper proposed a semi-supervised auto-encoder using sparse and label regularizations(LSRAE) to extract the essential features of the samples more accurately by combining unsupervised learning with supervised learning. The sparse regularization term added constraints to the response of each hidden node, so that this algorithm could find potential structures in the data when the number of hidden neurons was large. At the same time, this algorithm introduced a label regularization term to compare the actual labels with desired labels by supervised learning to adjust the network parameters and further improve the classification accuracy. In order to verify the validity of the proposed method, this algorithm tested many data sets in the experiment. The results show that compared with traditional auto-encoders(AE), sparse auto-encoder(SAE), and extreme learning machine(ELM), SLRAE can obviously improve the classification accuracy and stability when the processed data is applied to the same classifier.