首页> 外文会议>Intelligent Robots and Computer Vision X: Neural, Biological, and 3-D Methods >Effect of normalized interconnect matrix on the performance of Hopfield neural network
【24h】

Effect of normalized interconnect matrix on the performance of Hopfield neural network

机译:归一化互连矩阵对Hopfield神经网络性能的影响

获取原文
获取原文并翻译 | 示例

摘要

Abstract: It is shown by theoretical analysis and numerical simulations that there are some senses of reduction of the convergence property when the multi-valued matrix is substituted by a normalized matrix. Also, an optical experimental implementation scheme of a Hopfield neural network which uses a novel multi- valued synaptic interconnect matrix realized by a combined system of LCLV and CRT controlled by a microcomputer is proposed.!9
机译:摘要:通过理论分析和数值模拟表明,当用归一化矩阵代替多值矩阵时,收敛性有所降低。另外,提出了一种使用新型多值突触互连矩阵的Hopfield神经网络的光学实验实现方案,该结构由微机控制的LCLV和CRT组合系统实现。9

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