【24h】

An Improved Algorithm of Neural Network

机译:一种改进的神经网络算法

获取原文

摘要

Although the neural network has good function fitting, it has disadvantages such as slow convergence speed and easy to be trapped into local minimum. USES the input vector and the correlation of the objective function for the risk of slow convergence and local minima, the algorithm is improved, and several kinds of improved neural network algorithm for the practical validation, and the training also has carried on the comparison and analysis, it is concluded that the improved algorithm is effective, and has certain actual application value.
机译:虽然神经网络具有良好的功能拟合,但它具有较慢的收敛速度,易于陷入局部最小值。使用输入向量和对慢收敛风险的目标函数的相关性,算法得到改善,以及几种改进的神经网络算法,用于实际验证,培训也进行了比较和分析据结论,改进的算法是有效的,并且具有某些实际应用值。

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