首页> 外国专利> Feedback-tolerant method and device producing weight-adjustment factors for pre-synaptic neurons in artificial neural networks

Feedback-tolerant method and device producing weight-adjustment factors for pre-synaptic neurons in artificial neural networks

机译:人工神经网络中突触前神经元的容错方法和产生权重调整因子的设备

摘要

In an artificial neural network a method and neuron device that produce weight-adjustment factors, also called error values (116), for pre-synaptic neurons (302a . . . 302c) that are used to adjust the values of connection weights (106 . . . 106n) in neurons (100) used in artificial neural networks (ANNs). The amount of influence a pre-synaptic neuron has had over a post-synaptic neuron is calculated during signal propagation in the post-synaptic neuron (422a . . . 422n) and accumulated for the pre-synaptic neuron (426) for each post-synaptic neuron to which the pre-synaptic neuron's output is connected (428). Influence values calculated for use by pre-synaptic neurons may further be modified by the post-synaptic neuron's output value (102) (option 424), and its error value (116) (option 1110).
机译:在人工神经网络中,为突触前神经元( 302 a)产生权重调整因子(也称为误差值( 116 ))的方法和神经元设备.... 302 c ),用于调整连接权重( 106 ..。106 )的值人工神经网络(ANN)中使用的神经元( 100 )中的n )。在信号在突触后神经元( 422 a .. 422 n ),并为每个与突触前神经元输出连接的突触后神经元( 426 )积累( 428 )。可以通过突触后神经元的输出值( 102 )(选项 424 )及其误差值(< B> 116 )(选项 1110 )。

著录项

  • 公开/公告号US7814038B1

    专利类型

  • 公开/公告日2010-10-12

    原文格式PDF

  • 申请/专利权人 DOMINIC JOHN REPICI;

    申请/专利号US20070951611

  • 发明设计人 DOMINIC JOHN REPICI;

    申请日2007-12-06

  • 分类号G06F15/18;G06N3/08;

  • 国家 US

  • 入库时间 2022-08-21 18:52:37

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