首页> 外国专利> SEGMENTATION amp; RECOGNITION METHOD FOR PATTERNS OF OSCILLATORY NEURAL NETWORK

SEGMENTATION amp; RECOGNITION METHOD FOR PATTERNS OF OSCILLATORY NEURAL NETWORK

机译:振荡神经网络模式的分类识别方法

摘要

Inter nervous phase coupling in one floor is decided by feedback of selective oscillating of upper nerve, and selective oscillating of upper nervous by mutual control competition by matching linkage strength pattern from lower to upper. Therefore, oscillating of feature extraction nervous oscillating synchronized into one phase corresponds to one specific pattern and as for different patterns, feature extraction nerve corresponding to each conducts the segmentation and recognition of patterns by letting feature extraction nerve into different phases.
机译:一层中的神经间相耦合是由上神经的选择性振荡的反馈决定的,而上层神经的选择性振荡的反馈是通过相互控制竞争,通过从下到上匹配连锁强度模式来决定的。因此,特征提取神经的振荡在一个相位中同步地振动对应于一种特定的模式,并且对于不同的模式,对应于每个特征提取神经的振荡通过使特征提取神经进入不同的相位来进行模式的分割和识别。

著录项

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