...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Inteligencia Artificial : Ibero-American Journal of Artificial Intelligence >New training approaches for classification based on evolutionary neural networks. Application to product and sigmoidal units
【24h】

New training approaches for classification based on evolutionary neural networks. Application to product and sigmoidal units

机译：基于进化神经网络的新的分类训练方法。适用于产品和S形单位

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper sums up the main contributions of the PhD Dissertation with an homonymous name to the current article. Specifically, three contributions to train feed-forward neural network models based on evolutionary computation for a classification task are described. The new methodologies have been evaluated in three-layered neural models, including one input, one hidden and one output layer. Particularly, two kind of neurons such as product and sigmoidal units have been considered in an independent fashion for the hidden layer. Experiments have been carried out in a good number of problems, including three complex real-world problems, and the overall assessment of the new algorithms is very outstanding. Statistical tests shed light on that significant improvements were achieved. The applicability of the proposals is wide in the sense that can be extended to any kind of hidden neuron, either to other kind of problems like regression or even optimization with special emphasis in the two first approaches.
机译：本文总结了博士学位论文的主要贡献，并为本文冠以同名的名字。具体地，描述了基于分类任务的进化计算来训练前馈神经网络模型的三个贡献。新方法已在三层神经模型中进行了评估，包括一个输入，一个隐藏和一个输出层。特别地，已经针对隐藏层以独立的方式考虑了两种神经元，例如乘积和乙状单位。已经针对许多问题进行了实验，其中包括三个复杂的实际问题，并且对新算法的整体评估非常出色。统计测试表明取得了重大改进。在可以扩展到任何种类的隐藏神经元的意义上，这些建议的适用范围很广，可以扩展到其他类型的问题，例如回归，甚至可以优化两种最重要的方法。

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