首页> 外国专利> Artificial neural network learning device, distortion compensation circuit and signal processing device

Artificial neural network learning device, distortion compensation circuit and signal processing device

机译:人工神经网络学习装置,失真补偿电路和信号处理装置

摘要

The artificial neural network learning device (31) has a signal supply unit (40) that supplies a plurality of training signals to the signal processing circuit (11), and a signal memory (a signal memory) that stores the response signal output from the signal processing circuit (11). A plurality of randomly or pseudo-randomly selected selection signals are read from the 55) and the signal memory (55), and the plurality of selection signals are supplied to the artificial neural network structure (41) to supply the artificial neural network structure (41). ), A memory control unit (51) for outputting a plurality of post-distortion signals, and a learning control unit (61) are provided. The learning control unit (61) uses a plurality of error signals indicating the difference between the plurality of post-distortion signals and the plurality of teacher signals corresponding to the plurality of selection signals, and performs adaptive processing based on the back propagation learning algorithm. Is executed to update the parameter group of the artificial neural network structure (41).
机译:人工神经网络学习设备(31)具有信号供应单元(40),其向信号处理电路(11)提供多个训练信号,以及存储从响应信号输出的信号存储器(信号存储器)信号处理电路(11)。从55)读取多个随机或伪随机选择的选择信号,并且信号存储器(55),并且所述多个选择信号被提供给人工神经网络结构(41)以供应人工神经网络结构( 41)。 ),提供用于输出多个后失真信号的存储器控​​制单元(51)和学习控制单元(61)。学习控制单元(61)使用多个误差信号,指示多个后失真信号和对应于多个选择信号的多个教师信号之间的差异,并基于后传播学习算法执行自适应处理。被执行以更新人工神经网络结构的参数组(41)。

著录项

  • 公开/公告号JPWO2020157961A1

    专利类型

  • 公开/公告日2021-03-25

    原文格式PDF

  • 申请/专利权人 三菱電機株式会社;

    申请/专利号JP20200569314

  • 发明设计人 安藤 暢彦;

    申请日2019-02-01

  • 分类号H04B7/005;

  • 国家 JP

  • 入库时间 2024-06-14 21:23:23

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