• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Physica, A. Statistical mechanics and its applications >A dynamic model of evaluating differential automatic method for solving plane problems based on BP neural network algorithm
【24h】

A dynamic model of evaluating differential automatic method for solving plane problems based on BP neural network algorithm

机译：基于BP神经网络算法的求解平面问题的差分自动方法的动态模型

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

Aiming at solving differential equations of plane problems, the algorithm of difference equation is established, and the corresponding program is compiled on BP neural network. The correctness and practicability of the difference equation algorithm are verified. A dynamic model of the parallel difference equation is constructed according to the characteristics of the parallel structure of BP neural network. By calculating examples, the continuity condition under the condition of modulus abruption is further discussed. The study shows that the two groups of differential equations are used to identify and verify the model, and the energy function satisfies both the linear embedding condition and the correct wiring. Furthermore, BP neural network is used to realize the search and routing of the maximum plane. The results show that difference equation calculations have the ability to help BP networks get rid of local minima and get better results. (C) 2020 Published by Elsevier B.V.
机译：旨在求解平面问题的微分方程，建立了差分方程的算法，并且在BP神经网络上编译了相应的程序。 验证了差分等式算法的正确性和实用性。 平行差分方程的动态模型根据BP神经网络的并行结构的特性构建。 通过计算实施例，进一步讨论了模量突发性条件下的连续性条件。 该研究表明，两组微分方程用于识别和验证模型，并且能量函数满足线性嵌入条件和正确的布线。 此外，BP神经网络用于实现最大平面的搜索和路由。 结果表明，差异等式计算有能力帮助BP网络摆脱当地最小值并获得更好的结果。 （c）2020由elsevier b.v发布。

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