首页> 外国专利> PROCESSING OF HIGH-ORDER INFORMATION WITH NEURON NETWORK AND MINIMUM AND MAXIMUM VALUE SEARCHING METHOD THEREFOR

PROCESSING OF HIGH-ORDER INFORMATION WITH NEURON NETWORK AND MINIMUM AND MAXIMUM VALUE SEARCHING METHOD THEREFOR

机译:用神经网络和最小值和最大值搜索方法处理高阶信息

摘要

In order in Solve problems, with the processing speed of the construction and traditional neural network, optimal construction is employed synaptic neural network and is inferred based on the knowledge of the biological physiology or determined according to specific knowledgeization forecast processing function, including feature extraction function, the functions such as characteristic-integration function and memory. This makes it possible in image recognition and transfer control Application of Neural Network by passing through the ability for utilizing its parallel processing with extensive numerical value solution using its steady identification capacity or optimizing for problem.
机译:为了解决问题,以构造和传统神经网络的处理速度为基础,采用突触神经网络优化构造,并根据生物生理知识推论得出或根据特定的知识预测处理功能(包括特征提取功能)确定,特性集成功能和存储等功能。通过利用其具有稳定的识别能力或针对问题进行优化的广泛数值解决方案来利用其并行处理能力,这使得在神经网络的图像识别和传输控制应用中成为可能。

著录项

  • 公开/公告号EP0366804A4

    专利类型

  • 公开/公告日1991-01-23

    原文格式PDF

  • 申请/专利权人 HITACHI LTD.;

    申请/专利号EP19890903795

  • 发明设计人 MATSUBA IKUO;MINAMI KEIKO;

    申请日1989-03-24

  • 分类号G06F15/70;

  • 国家 EP

  • 入库时间 2022-08-22 05:53:33

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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