代价敏感正则化有限记忆多隐层在线序列极限学习机及图像识别应用

宋坤骏; 丁建明

代价敏感正则化有限记忆多隐层在线序列极限学习机及图像识别应用

西南交通大学牵引动力国家重点实验室,成都 610031

详细信息

作者简介:
宋坤骏,在读硕士研究生;丁建明,副教授。

中图分类号: TP39
计量
- 文章访问数: 66
- HTML全文浏览量: 0
- PDF下载量: 22
出版历程
- 收稿日期: 2017-11-28
- 刊出日期: 2018-05-24

Cost-sensitive regularized finite-memory multi-hidden-layer online sequential extreme learning machine and its application in image recognition

State Key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu 610031, China

摘要

摘要: 将深度神经网络的多隐层特性融入在线序列极限学习机框架,提出代价敏感正则化有限记忆多隐层在线序列极限学习机,其中,代价敏感性由加权最小二乘法体现,有限记忆性通过及时丢弃过时旧数据体现。实验结果表明,加入了多隐层特性的在线序列极限学习机在图像识别准确率上比单隐层的在线序列极限学习机有所提升,在识别准确率的稳定性方面也比单隐层网络更出色。
- 代价敏感 /
- 有限记忆 /
- 多隐层在线序列极限学习机 /
- 图像识别
Abstract: The multiple hidden layers characteristic of deep neural networks was integrated into the framework of online sequential extreme learning machine. Thereby the author proposed a new algorithm called cost-sensitive regularized finite-memory multi-hidden-layer online sequential extreme learning machine. Cost sensitivity was embodied by the method of weighted least squares whereas the property of finite memory was embodied by discard of old obsolete data. Experiment results show that the online sequential extreme learning machines with the property of multiple hidden layers have higher image recognition accuracy and higher stability of recognition accuracy than that of single-hidden-layer.
- cost-sensitive /
- finite-memory /
- multi-hidden-layer online sequential extreme learning machine /
- image recognition

HTML全文

参考文献(13)

[1]	He K, Zhang X, Ren S, et al.Deep Residual Learning for Image Recognition[C]// Computer Vision and Pattern Recognition. IEEE, 2016:770-778.
[2]	Panda P, Sengupta A, Roy K.Energy-Efficient and Improved Image Recognition with Conditional Deep Learning[J]. Acm Journal on Emerging Technologies in Computing Systems, 2017, 13(3):1-21.
[3]	Miyazono T, Saitoh T.Fish Species Recognition Based on CNN Using Annotated Image[C]// International Conference on Information Theoretic Security. Springer, Singapore, 2017:156-163.
[4]	Huang G.B., Zhu Q Y., Siew C.K.Extreme learning machine: theory and Applications[J]. Neurocomputing, 2006, 70(1): 489-501.
[5]	Yang Y, Wang Y, Yuan X.Bidirectional Extreme Learning Machine for Regression Problem and Its Learning Effectiveness[J]. IEEE Transactions on Neural Networks & Learning Systems, 2012, 23(9):1498-1505.
[6]	Cao J, Lin Z, Huang G B, et al.Voting based extreme learning machine[J]. Information Sciences, 2012, 185(1): 66-77.
[7]	Liu X, Gao C, Li P.A comparative analysis of support vector machines and extreme learning machines[J]. Neural Networks, 2012, 33(9): 58.
[8]	Yu, D., Deng, L.Efficient and effective algorithms for training single hidden-layer neural networks[J]. Pattern Recognition Letters,2012, 33(5): 554-558
[9]	张弦,王宏力. 限定记忆极端学习机及其应用[J]. 控制与决策,2012,27(8):1206-1210.
[10]	Tang J, Deng C, Huang G B.Extreme Learning Machine for Multilayer Perceptron[J]. IEEE Transactions on Neural Networks & Learning Systems, 2017, 27(4):809-821.
[11]	Deng C Y.A generalization of the Sherman-Morrison-Woodbury formula[J]. Applied Mathematics Letters, 2011, 24(9):1561-1564.
[12]	Blocki J, Blum A, Datta A, et al.The Johnson-Lindenstrauss Transform Itself Preserves Differential Privacy[C]// IEEE, Symposium on Foundations of Computer Science. IEEE Computer Society, 2012:410-419.
[13]	Bartlett P.The sample complexity of pattern classification with neural networks: the size of theweights is more important than the size of the network[J]. IEEE Transactions on InformationTheory. 1998, 44(2): 525-536.

施引文献(4)

期刊类型引用(4)

1.	邱妍妍，高增. 基于低秩分解的异常步态活动图像序列识别. 计算机仿真. 2021(06): 415-418 . 百度学术
2.	杨基宏，陈浩林，徐刚，余澄庆，刘辉. 基于ELM的城市轨道交通系统建设成本估算研究. 铁路计算机应用. 2020(04): 1-4 . 本站查看
3.	彭桂容. 运用图像培养学生的记忆素质. 文科爱好者(教育教学). 2019(02): 187+189 . 百度学术
4.	陈紫薇，张渝，邱春蓉. 基于PSO–MK–ELM的动车轮对尺寸预测模型. 铁路计算机应用. 2019(12): 15-19 . 本站查看