首页> 外国专利> Algorithms and circuitry for verifying stored values during programming operations of non-volatile memory cells in analog neural memory in deep learning artificial neural networks

Algorithms and circuitry for verifying stored values during programming operations of non-volatile memory cells in analog neural memory in deep learning artificial neural networks

机译:用于在深度学习人工神经网络中的模拟神经记忆中的非易失性存储器单元的编程操作期间验证存储值的算法和电路

摘要

After a multilevel programming operation of a non-volatile memory cell, various algorithms are disclosed for verifying the stored weight of a non-volatile memory cell in a neural network by converting the stored weight into a plurality of digital output bits. Circuitry such as an adjustable reference current source for implementing algorithms is disclosed.
机译:在非易失性存储器单元的多级编程操作之后,公开了用于通过将存储的权重转换为多个数字输出位来验证神经网络中的非易失性存储器单元的存储权重的各种算法。 公开了用于实现算法的可调参考电流源的电路。

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