首页> 外文会议>International Symposium on Neural Networks >A New Strategy for Designing Bidirectional Associative Memories
【24h】

A New Strategy for Designing Bidirectional Associative Memories

机译:设计双向联想记忆的新策略

获取原文

摘要

A comprehensive strategy for bidirectional associative memories (BAMs) is presented, which enhances storage capacity greatly. The design strategy combines the dummy augmentation encoding method with optimal gradient descent algorithm. The proposed method increases the storage capacity performance of BAM to its upper limit compared with original Kosko method and optimal gradient descent algorithm. Computer simulations and comparison are given based on three methods to demonstrate the performance improvement of the proposed strategy.
机译:提出了一种对双向联合记忆(BAM)的综合策略,从而大大提高了存储容量。设计策略与最优梯度下降算法结合了虚拟增强编码方法。该方法将BAM的存储容量性能提高到其上限与原始KOSKO方法和最佳梯度下降算法相比。基于三种方法来证明拟议策略的绩效改进,给出了计算机仿真和比较。

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