• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

关于《用于动态系统控制的对角递归神经网络》的评论。定理2和定理4的证明[及回复]

Comments on "Diagonal recurrent neural networks for dynamic systems control". Reproof of theorems 2 and 4 [and reply].

作者信息

Liang X, Lee K Y

机构信息

Dept. of Electr. Eng., New Brunswick Univ., Fredericton, NB.

出版信息

IEEE Trans Neural Netw. 1997;8(3):811-4. doi: 10.1109/72.572120.

DOI:10.1109/72.572120
PMID:18255684
Abstract

In their original paper, C.-C. Ku and K.Y. Lee (ibid., vol.6, p.144-56, 1995) designed a diagonal recurrent neural network architecture for control systems. Liang asserts that a condition assumed in the proof of its convergence does not necessarily apply, and presents alternative theorems and proofs. Lee replies that Liang has misunderstood the original paper, and also that he made mistakes in his new proofs, but acknowledges that the original paper did not go into full detail about how a limitation would be implemented. Lee also presents a revision for the case of time-varying weights.

摘要

在他们的原始论文中,C.-C. Ku和K.Y. Lee(同上,第6卷,第144 - 156页,1995年)为控制系统设计了一种对角递归神经网络架构。Liang声称其收敛性证明中所假设的一个条件不一定适用,并给出了替代定理和证明。Lee回应称Liang误解了原始论文,并且他在新的证明中也犯了错误,但承认原始论文没有详细说明如何实施一种限制。Lee还针对时变权重的情况给出了一个修正。

相似文献

1
Comments on "Diagonal recurrent neural networks for dynamic systems control". Reproof of theorems 2 and 4 [and reply].关于《用于动态系统控制的对角递归神经网络》的评论。定理2和定理4的证明[及回复]
IEEE Trans Neural Netw. 1997;8(3):811-4. doi: 10.1109/72.572120.
2
Diagonal recurrent neural networks for dynamic systems control.
IEEE Trans Neural Netw. 1995;6(1):144-56. doi: 10.1109/72.363441.
3
Comments on "A training rule which guarantees finite-region stability for a class of closed-loop neural-network control systems" [with reply].关于《一类闭环神经网络控制系统的有限区域稳定性保证训练规则》的评论[附回应]
IEEE Trans Neural Netw. 1997;8(5):1217-8. doi: 10.1109/72.623225.
4
Comments on ;Dynamic programming approach to optimal weight selection in multilayer neural networks' [with reply].关于《多层神经网络中最优权重选择的动态规划方法》的评论[及回复]
IEEE Trans Neural Netw. 1992;3(6):1028-9. doi: 10.1109/72.165609.
5
Comments on ;parallel algorithms for finding a near-maximum independent set of a circle graph' [with reply].
IEEE Trans Neural Netw. 1991;2(2):328-9. doi: 10.1109/72.80347.
6
A complete proof of global exponential convergence of a neural network for quadratic optimization with bound constraints.具有边界约束的二次优化神经网络全局指数收敛的完整证明。
IEEE Trans Neural Netw. 2001;12(3):636-9. doi: 10.1109/72.925567.
7
Comments on ;Bayes statistical behavior and valid generalization of pattern classifying neural networks' [with reply].关于《贝叶斯统计行为与模式分类神经网络的有效泛化》的评论[并附回复]
IEEE Trans Neural Netw. 1992;3(6):1026-7. doi: 10.1109/72.165607.
8
Comments on "discrete time neural network synthesis using input and output functions".关于《使用输入和输出函数的离散时间神经网络合成》的评论
IEEE Trans Syst Man Cybern B Cybern. 2000;30(1):244-5. doi: 10.1109/3477.826968.
9
Adaptive hybrid control for linear piezoelectric ceramic motor drive using diagonal recurrent CMAC network.基于对角递归小脑模型关节控制器网络的线性压电陶瓷电机驱动自适应混合控制
IEEE Trans Neural Netw. 2004 Nov;15(6):1491-506. doi: 10.1109/TNN.2004.837784.
10
Improved conditions for global exponential stability of recurrent neural networks with time-varying delays.具有时变时滞的递归神经网络全局指数稳定性的改进条件。
IEEE Trans Neural Netw. 2006 May;17(3):623-35. doi: 10.1109/TNN.2006.873283.