• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Joint Conference on Neural Networks >Dynamic sample size selection based quasi-Newton training for highly nonlinear function approximation using multilayer neural networks
【24h】

Dynamic sample size selection based quasi-Newton training for highly nonlinear function approximation using multilayer neural networks

机译：基于动态样本量选择的准牛顿训练，用于使用多层神经网络进行高度非线性函数逼近

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper describes a novel robust training algorithm based on quasi-Newton iteration. The size of training samples for each iteration is dynamically and analytically determined by variance estimates during the computation of its gradient in the mini-batch based online training methodology. Furthermore, the size of mini-batch is controlled by a parameter to ensure that the number of samples in a mini-batch changes from a portion of samples (online) to all ones (batch) as quasi-Newton iteration progressed. As a result, the iteration during online mode can be shortened compared with previous quasi-Newton-based methods in which the gradient of error function for the training step was improved.
机译：本文描述了一种基于拟牛顿迭代的鲁棒训练算法。在基于小批量的在线培训方法中，通过计算梯度时可以通过方差估计来动态地分析确定每次迭代的训练样本的大小。此外，小批量的大小由参数控制，以确保随着准牛顿迭代的进行，小批量中的样本数从一部分样本（在线）更改为所有样本（批）。结果，与以前的基于准牛顿的方法相比，在线模式下的迭代可以缩短，在以前的准牛顿方法中，训练步骤的误差函数的梯度得到了改善。

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