...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neurocomputing >DropELM: Fast neural network regularization with Dropout and DropConnect
【24h】

DropELM: Fast neural network regularization with Dropout and DropConnect

机译：DropELM：使用Dropout和DropConnect进行快速神经网络正则化

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we propose an extension of the Extreme Learning Machine algorithm for Single-hidden Layer Feedforward Neural network training that incorporates Dropout and DropConnect regularization in its optimization process. We show that both types of regularization lead to the same solution for the network output weights calculation, which is adopted by the proposed DropELM network. The proposed algorithm is able to exploit Dropout and DropConnect regularization, without computationally intensive iterative weight tuning. We show that the adoption of such a regularization approach can lead to better solutions for the network output weights. We incorporate the proposed regularization approach in several recently proposed ELM algorithms and show that their performance can be enhanced without requiring much additional computational cost. (C) 2015 Elsevier B.V. All rights reserved.
机译：在本文中，我们提出了用于单隐藏层前馈神经网络训练的极限学习机算法的扩展，该算法在优化过程中结合了Dropout和DropConnect正则化。我们表明，两种类型的正则化都为网络输出权重计算带来了相同的解决方案，而拟议的DropELM网络采用了这种解决方案。所提出的算法能够利用Dropout和DropConnect正则化，而无需进行计算密集的迭代权重调整。我们表明，采用这种正则化方法可以为网络输出权重提供更好的解决方案。我们将提出的正则化方法纳入了几种最近提出的ELM算法中，并表明可以提高它们的性能而无需太多额外的计算成本。 （C）2015 Elsevier B.V.保留所有权利。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号