首页> 外文会议>International Conference on Hydroinformatics >ADVANCES IN NEURAL NETWORK HYDROLOGICAL MODELLING: AN ADAPTIVE CO-EVOLUTIONARY APPROACH
【24h】

ADVANCES IN NEURAL NETWORK HYDROLOGICAL MODELLING: AN ADAPTIVE CO-EVOLUTIONARY APPROACH

机译:神经网络水文建模的进步:自适应共进方法

获取原文

摘要

This paper presents JavaSANE, a system that advances on traditional evolutionary approaches by evolving and optimising individual neurons. JavaSANE was used to evolve neural network rainfall-runoff solutions for the River Ouse catchment in the UK using several different objective functions. These results were compared against a standard backpropagation network. The results show that (ⅰ) as lead times increase the JavaSane networks outperform the standard networks and (ⅱ) SSE is not the best objective function.
机译:本文介绍了爪哇,一种通过演化和优化个体神经元进行传统进化方法的系统。 Javasane用于使用几种不同的客观函数在英国的河流集水区演变神经网络降雨解决方案。将这些结果与标准的背部化网络进行比较。结果表明,(Ⅰ)随着报酬时间增加,爪哇网络优于标准网络,(Ⅱ)SSE不是最佳的客观函数。

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