A Constrained Optimization Approach to Preserving Prior Knowledge in Neural-Network Modeling and Control of Dynamical Systems

在神经网络建模和动力系统控制中保留先验知识的约束优化方法

• 批准号: 0823945
• 负责人: Silvia Ferrari
• 金额: $ 32.21万
• 依托单位: Duke University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2008
• 资助国家: 美国
• 起止时间: 2008-08-01 至 2014-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0823945&HistoricalAwards=false
• 关键词: Constrained; Optimization; Approach; Preserving; Prior

Proposal Number: ECCS-0823945Proposal Title: A Constrained Optimization Approach to Preserving Prior Knowledge in Neural-Network Modeling and Control of Dynamical SystemsPI Name: Ferrari, SilviaPI Institution: Duke UniversityThe objective of this research is to develop and implement a unified theory for memory and forgetting in artificial neural networks. The novel learning algorithms developed through this research will eliminate interference and catastrophic interference in nonlinear and fully-connected neural networks, thereby enhancing their applicability in a number of engineering applications. The approach is to formulate learning through a constrained backpropagation approach that optimizes the neural network performance subject to long-term memory constraints, which may be deteriorated over time via a penalty function or Lagrange multipliers.Intellectual MeritThe intellectual merit of the proposed research is the development of a novel constrained backpropagation approach that combines constrained optimization theory and classical backpropagation. The newly developed adjoined error gradient and algebraic training formalisms together allow to formulate constrained backpropagation efficiently and effectively, while also exploiting existing artificial neural networks algorithms, such as Levenberg-Marquardt and resilient backpropagation.Broader ImpactThe proposed activity will enhance the applicability and effectiveness of on-line adaptive neural networks in a broad spectrum of complex science and engineering problems, namely, function approximation, solution of differential equations, system identification, and control. The constrained-backpropagation theory and algorithms will be implemented on data-assimilation problems, which will benefit society by producing timely predictions about environmental change and dispersion of urban pollutants, and on adaptive dual control, which will produce flight control systems that are fault and damage-tolerant, and make piloted airplanes safer and easier to fly. Also, they will be demonstrated through benchmark problems in robotics and mine hunting using Graphical User Interfaces, for educational and dissemination purposes. This approach has already been proven successful at creating positive synergies and collaborations between Duke University and K-12 students from the Chapel Hill (NC) public schools, as well as small local industries.

提案编号：ECCS-0823945 提案标题：在神经网络建模和动态系统控制中保留先验知识的约束优化方法 PI 名称：Ferrari, Silvia PI 机构：杜克大学 这项研究的目标是开发和实现记忆和控制的统一理论。人工神经网络中的遗忘。 通过这项研究开发的新型学习算法将消除非线性和全连接神经网络中的干扰和灾难性干扰，从而增强其在许多工程应用中的适用性。 该方法是通过约束反向传播方法来制定学习，该方法优化受长期记忆约束的神经网络性能，长期记忆约束可能会随着时间的推移通过惩罚函数或拉格朗日乘数而恶化。 智力优点所提议的研究的智力优点是开发一种新颖的约束反向传播方法，结合了约束优化理论和经典反向传播。 新开发的邻接误差梯度和代数训练形式一起允许高效且有效地制定约束反向传播，同时还利用现有的人工神经网络算法，例如Levenberg-Marquardt和弹性反向传播。更广泛的影响所提出的活动将增强其适用性和有效性线自适应神经网络在广泛的复杂科学和工程问题中的应用，即函数逼近、微分方程的求解、系统识别和控制。 约束反向传播理论和算法将应用于数据同化问题，通过对环境变化和城市污染物扩散的及时预测来造福社会，以及自适应双控制，这将产生故障和损坏的飞行控制系统- 宽容，使有人驾驶的飞机更安全、更容易飞行。 此外，它们还将通过使用图形用户界面的机器人和探雷中的基准问题进行演示，以用于教育和传播目的。 事实证明，这种方法在杜克大学和来自教堂山 (NC) 公立学校的 K-12 学生以及当地小型企业之间建立积极的协同效应和合作方面已经取得了成功。