课题基金 / 基金详情

A Qualitative Study of Time-Lagged Recurrent Networks

A Qualitative Study of Time-Lagged Recurrent Networks
时滞循环网络的定性研究
批准号:
9732785
负责人:
Derong Liu
金额:
$11.63万
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
1998
资助国家:
美国
项目状态:
已结题
起止时间:
1998-09-01 至 2000-07-31

项目摘要

项目成果

Derong Liu的其他基金

相似基金

相关文献

中文摘要
翻译
ECS-9732785LiuTime-Return递归网络(Tlrn)在非线性系统辨识和控制方面比前馈多层神经网络更有效。本项目将在两个方面研究TLRN的几个基本的重要理论和实践问题:结构自适应性和稳健性分析:对于使用神经网络的非线性函数逼近,将研究时滞递归网络的行为与前馈神经网络的比较。结果表明,由于网络中递归的存在,时滞递归网络将表现出与具有时变参数的多层前馈神经网络等价的行为。具有时变参数的多层前馈神经网络有望表现出自适应行为,而研究表明具有固定参数的时滞递归网络一般将表现出自适应行为。此外,还将深入研究时滞递归网络在参数扰动下的性能。基于能量函数方法的训练:递归神经网络的稳定性是最重要的,它可以转化为收敛的行为和网络中的信号和参数的边界。用李雅普诺夫第二方法研究时滞递归网络的稳定性。在应用Lyapunov第二方法时,需要构造一个Lyapunov函数(或能量函数)。稳定性是由放屁保证的,即Lyapunov函数是正定的,并且(单调地)随时间递减。这一稳定性分析结果将为用于系统辨识的神经网络的训练提供新的线索,这将导致训练算法保证收敛于全局最小值或解。
英文摘要
ECS-9732785LiuTime-Lagged Recurrent Networks (TLRN)are known to be more powerful than feedforward multilayer neural networks and in nonlinear systems identification and control. This project will investigate several fundamentally important theoretical and practical questions concerning TLRN's in two areas:Structural adaptivity and robustness analysis: For nonlinear functionapproximation using neural networks, the behavior of time-laggedrecurrent networks will be studied in comparison to feedforward neural networks. It will be shown that, due to the existence of recurrencies in the network,time-lagged recurrent networks will exhibit behavior equivalent tomultilayer feedforward neural networks with time-varying parameters. It isexpected that a multilayer feedforward neural network with time-varyingpaxameters will exhibit adaptive behavior; and the study will show that time-lagged recurrent networks with fixed parameters will generally exhibit adaptivebehavior. A thorough study of how time-lagged recurrent networks willperform under parameter perturbations will also be conducted. Resultswill be given as bounds for permissible parameter perturbations whichguarantee to retain the desired performance of the network.Training based on energy function approach: Stability of recurrentNeural networks which can be translated into convergent behavior and boundedsignals and parameters in the network is of fundamental interest. Thestability properties of tiine-lagged recurrent networks will be studiedusing the Lyapunov's second method. In applying the Lyapunov second method, oneneeds to construct a Lyapunov function (or energy function). Stability isguaranteed by the fart that the Lyapunov function is positive definite andis (monotonically) decreasing over time. This stability analysis result willshed new lights on the training of neural networks for systems identification,which will lead to training algorithms with guaranteed convergence to the globalminimum or to a solution.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
EAGER: Adaptive Dynamic Programming for Residential Energy System Control and Management
  • 批准号:
    1027602
  • 项目类别:
    Standard Grant
  • 资助金额:
    $11.9万
  • 财政年份:
    2010
  • 负责人:
    Derong Liu
  • 依托单位:
Finite Horizon Discrete-Time Adaptive Dynamic Programming
  • 批准号:
    0621694
  • 项目类别:
    Standard Grant
  • 资助金额:
    $24.0万
  • 财政年份:
    2006
  • 负责人:
    Derong Liu
  • 依托单位:
Neural Dynamic Programming for Automotive Engine Control
  • 批准号:
    0355364
  • 项目类别:
    Continuing Grant
  • 资助金额:
    $10.0万
  • 财政年份:
    2004
  • 负责人:
    Derong Liu
  • 依托单位:
Power Control and Call Admission Policies for Multiclass Traffic in SIR-Based Power-Controlled DS-CDMA Cellular Networks
  • 批准号:
    0203063
  • 项目类别:
    Standard Grant
  • 资助金额:
    $30.0万
  • 财政年份:
    2002
  • 负责人:
    Derong Liu
  • 依托单位:
国内基金
海外基金
Incentive and governance schenism study of corporate green washing behavior in China: Based on an integiated view of econfiguration of environmental authority and decoupling logic
  • 批准号:
    --
  • 项目类别:
    外国学者研究基金项目
  • 资助金额:
    --
  • 批准年份:
    2024
  • 负责人:
    YU BYUNGJUN
  • 依托单位:
A study on prototype flexible multifunctional graphene foam-based sensing grid (柔性多功能石墨烯泡沫传感网格原型研究)
  • 批准号:
    --
  • 项目类别:
    --
  • 资助金额:
    20万元
  • 批准年份:
    2020
  • 负责人:
    SAGAR RIZWAN UR REHMAN
  • 依托单位: