首页> 外国专利> SYSTEM AND METHOD FOR SELF CONSTRUCTING DEEP NEURAL NETWORK DESIGN THROUGH ADVERSARIAL LEARNING

SYSTEM AND METHOD FOR SELF CONSTRUCTING DEEP NEURAL NETWORK DESIGN THROUGH ADVERSARIAL LEARNING

机译:通过逆向学习自我构建深层神经网络设计的系统和方法

摘要

The present disclosure is directed to a novel system for a self-constructing deep neural network. The system may comprise a hybrid logic library which contains the building structures needed to construct the neural network, which may include both traditional logic and memory structures as well as learning structures. In constructing the neural network from library structures, the system may use an algorithm to iteratively improve the performance of the neural network. In this way, the system may provide a way to generate complex neural networks that become increasingly optimized over time.
机译:本公开针对一种用于自构造深度神经网络的新颖系统。该系统可以包括混合逻辑库,该混合逻辑库包含构造神经网络所需的构造结构,该结构可以包括传统逻辑和存储器结构以及学习结构。在从库结构构造神经网络时,系统可以使用算法来迭代地改善神经网络的性能。以这种方式,系统可以提供一种生成复杂的神经网络的方式,该网络随着时间的流逝越来越优化。

著录项

  • 公开/公告号US2020175371A1

    专利类型

  • 公开/公告日2020-06-04

    原文格式PDF

  • 申请/专利权人 BANK OF AMERICA CORPORATION;

    申请/专利号US201816209363

  • 发明设计人 EREN KURSUN;

    申请日2018-12-04

  • 分类号G06N3/08;G06N3/04;G06K9/62;G06F17/11;

  • 国家 US

  • 入库时间 2022-08-21 11:19:49

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