• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>The 9th World Multi-Conference on Systemics, Cybernetics and Informatics(WMSCI 2005) vol.7 >Backpropagation and Recurrent Neural Networks for Thai Exports and Gross Domestic Product Forecasting
【24h】

Backpropagation and Recurrent Neural Networks for Thai Exports and Gross Domestic Product Forecasting

机译：用于泰国出口和国内生产总值预测的反向传播和递归神经网络

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

Applications of neural networks in forecasting require treatment of dynamics associated with the input signal. Feedforward neural networks (FNNs) for processing of dynamical systems tend to capture the dynamics by including past inputs in the input vector. However, for dynamical modelling of complex systems, there is a need to involve feedback and this leads to the use of Recurrent Neural Networks(RNNs).In addition to the various features of FNNs, RNNs allow the output from selfloops and backward connections between nodes. One of the main reasons for being interested is that there are new proposed algorithms which allow them to learn how to interact with an environment in an appropriate way. However, most RNN's training algorithms suffer from the slow convergence, high complexity in determining the gradient of the related (sum of squared)errors, and also very sensitive to the choice of learning rate and initial values of the weights. In order to compare the performance of the different architectures and algorithms of the backpropagation algorithm of FNN and those of the RNNs in terms of prediction accuracy and computational time. An empirical study was carried out based on the quarterly data on exports and gross domestic product (GDP) of Thailand. The proposed algorithm has for faster convergence performance than the Backpropagation. The new training algorithm on a RNN could forecast the exports and GDP quite satisfactorily.
机译：神经网络在预测中的应用要求处理与输入信号相关的动力学。用于处理动力学系统的前馈神经网络（FNN）倾向于通过将过去的输入包括在输入向量中来捕获动力学。但是，对于复杂系统的动态建模，需要涉及反馈，这导致使用递归神经网络（RNN）.RNN除了具有FNN的各种功能外，还允许自环输出和节点之间的反向连接。感兴趣的主要原因之一是，提出了新的算法，使他们能够学习如何以适当的方式与环境交互。但是，大多数RNN的训练算法受收敛速度慢，确定相关（平方和）误差的梯度的复杂性高以及对学习率和权重初始值的选择非常敏感。为了在预测精度和计算时间方面比较FNN和RNN的反向传播算法的不同体系结构和算法的性能。根据有关泰国出口和国内生产总值（季度）的季度数据进行了实证研究。所提出的算法具有比反向传播更快的收敛性能。 RNN上的新训练算法可以相当令人满意地预测出口和GDP。

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