首页> 外文期刊>Mathematical Problems in Engineering >Data Normalization to Accelerate Training for Linear Neural Net to Predict Tropical Cyclone Tracks
【24h】

Data Normalization to Accelerate Training for Linear Neural Net to Predict Tropical Cyclone Tracks

机译:数据归一化可加速线性神经网络的训练,以预测热带气旋的轨迹

获取原文
获取原文并翻译 | 示例
           

摘要

When pure linear neural network (PLNN) is used to predict tropical cyclone tracks (TCTs) in South China Sea, whether the data is normalized or not greatly affects the training process. In this paper, min.-max. method and normal distribution method, instead of standard normal distribution, are applied to TCT data before modeling. We propose the experimental schemes in which, with min.-max. method, the min.-max. value pair of each variable is mapped to (-1, 1) and (0, 1); with normal distribution method, each variable's mean and standard deviation pair is set to (0, 1) and (100, 1). We present the following results: (1) data scaled to the similar intervals have similar effects, no matter the use of min.-max. or normal distribution method; (2) mapping data to around 0 gains much faster training speed than mapping them to the intervals far away from 0 or using unnormalized raw data, although all of them can approach the same lower level after certain steps from their training error curves. This could be useful to decide data normalization method when PLNN is used individually.
机译:当使用纯线性神经网络(PLNN)预测南中国海的热带气旋路径(TCT)时,数据是否被规范化会极大地影响训练过程。在本文中,最小-最大。方法和正态分布方法(而不是标准正态分布)在建模之前应用于TCT数据。我们提出了实验方案,其中最小-最大。方法,最小-最大每个变量的值对映射到(-1,1)和(0,1);使用正态分布方法,每个变量的均值和标准差对设置为(0,1)和(100,1)。我们得出以下结果:(1)无论使用最小-最大,缩放到相似间隔的数据都具有相似的效果。或正态分布方法; (2)将数据映射到0左右比将其映射到远离0的间隔或使用未规范化的原始数据要快得多,尽管它们从训练误差曲线经过某些步骤后都可以达到相同的较低水平,但训练速度要快得多。当单独使用PLNN时,这对于决定数据标准化方法可能很有用。

著录项

  • 来源
    《Mathematical Problems in Engineering》 |2015年第12期|931629.1-931629.8|共8页
  • 作者

    Jin Jian; Li Ming; Jin Long;

  • 作者单位

    E China Normal Univ, Dept Comp Sci & Technol, Shanghai 200241, Peoples R China;

    E China Normal Univ, Shanghai Key Lab Multidimens Informat Proc, Shanghai 200241, Peoples R China;

    Guangxi Climate Ctr, Guangxi Meteorol Bur, Nanning 530022, Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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