首页> 外文会议>International conference on signal processing;ICSP '98 >Extraction of Logic rules on the basis of robust binary feedforward neural networks
【24h】

Extraction of Logic rules on the basis of robust binary feedforward neural networks

机译:基于鲁棒二进制前馈神经网络的逻辑规则提取

获取原文

摘要

This paper, on the basis of connection weights of robust binary feedforward neural networks (robust BNNs) being -1,0 or +1, presents a fact that the extraction of logic rules from robust BNNs is much eeasier than that from ordinary feeforward neural networks, and robust BNNs are perfect unification of logic knowledge database, inference machine and interpretation machine.
机译:本文基于健壮的二进制前馈神经网络(健壮的BNN)的连接权重为-1,0或+1,提出了一个事实,即从健壮的BNN中提取逻辑规则比从普通的前馈神经网络中提取逻辑规则更容易强大的BNN是逻辑知识数据库,推理机和解释机的完美统一。

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