| 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 |
| |
| 引用本文： | 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[J].铁路计算机应用,2018,27(5):18-23. |
| |
| 作者姓名： | 宋坤骏 丁建明 |
| |
| 作者单位： | 西南交通大学 牵引动力国家重点实验室,成都 610031 |
| |
| 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。
|
| 关 键 词： | 代价敏感 有限记忆 多隐层在线序列极限学习机 图像识别 |
| 收稿时间： | 2017-11-29 |
Cost-sensitive regularized finite-memory multi-hidden-layer online sequential extreme learning machine and its application in image recognition |
| |
| Affiliation: | State Key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu 610031, China |
| |
| 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. |
| |
| Keywords: | |
|
| 点击此处可从《铁路计算机应用》浏览原始摘要信息 |
|
点击此处可从《铁路计算机应用》下载全文 |
