期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
基于栈式降噪稀疏自编码器的极限学习机 认领 引用 被引量:14
1
作者 张国令 王晓丹 +2 位作者 李睿 来杰 向前 《计算机工程》 CAS CSCD 北大核心 2020年第9期61-67,共7页
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... 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。 展开更多
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
暂未订购 下载PDF
A Cloud Computing Fault Detection Method Based on Deep Learning 认领 引用 被引量:2
2
作者 Weipeng Gao Youchan Zhu 《Journal of Computer and Communications》 2017年第12期24-34,共11页
In the cloud computing, in order to provide reliable and continuous service, the need for accurate and timely fault detection is necessary. However, cloud failure data, especially cloud fault feature data acquisition ... In the cloud computing, in order to provide reliable and continuous service, the need for accurate and timely fault detection is necessary. However, cloud failure data, especially cloud fault feature data acquisition is difficult and the amount of data is too small, with large data training methods to solve a certain degree of difficulty. Therefore, a fault detection method based on depth learning is proposed. An auto-encoder with sparse denoising is used to construct a parallel structure network. It can automatically learn and extract the fault data characteristics and realize fault detection through deep learning. The experiment shows that this method can detect the cloud computing abnormality and determine the fault more effectively and accurately than the traditional method in the case of the small amount of cloud fault feature data. 展开更多
关键词 Fault Detection Cloud Computing Auto-Encoder Sparse Denoising Deep Learning
暂未订购 下载PDF
上一页 1 下一页 到第
在线咨询 使用帮助 返回顶部 意见反馈