摘要： 极限学习机（ELM）随机选择网络输入权重和隐层偏置，存在网络结构复杂和鲁棒性较弱的不足。为此，提出基于栈式降噪稀疏自编码器（sDSAE）的ELM算法。利用sDSAE稀疏网络的优势，挖掘目标数据的深层特征，为ELM产生输入权值与隐层偏置以求得隐层输出权值，完成训练分类器，同时通过加入稀疏性约束优化网络结构，提高算法分类准确率。实验结果表明，与ELM、PCA-ELM、ELM-AE和DAE-ELM算法相比，该算法在处理高维含噪数据时分类准确率较高，并且具有较强的鲁棒性。

关键词: 极限学习机, 降噪稀疏自编码器, 稀疏性, 深度学习, 特征提取

Abstract: Extreme Learning Machine(ELM)randomly selects input weights and hidden-layer bias of network,which increases the complexity and reduces the robustness of network.To address the problem,this paper proposes an ELM algorithm based on stacked Denoising Sparse Auto-Encoder(sDSAE-ELM).By taking the advantage of sparse network of stacked Denoising Sparse Auto-Encoder(sDSAE),the deep features of target data are mined,and the input weight and hidden-layer bias are generated for ELM to obtain the hidden-layer output weight,and the training classifier is completed.Then sparsity constraints are added to optimize the network structure and improve the accuracy of algorithm classification.Experimental results show that the proposed algorithm has higher classification accuracy and stronger robustness than ELM,PCA-ELM,ELM-AE and DAE-ELM algorithms in processing of high-dimensional noisy data.

Key words: Extreme Learning Machine(ELM), Denoising Sparse Auto-Encoder(DSAE), sparsity, deep learning, feature extraction

中图分类号: 

• TP181