Strategies for Better System Identification

更好的系统识别策略

• 批准号: 9114333
• 负责人: John Moody
• 金额: $ 6.54万
• 依托单位: Yale University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1991
• 资助国家: 美国
• 起止时间: 1991-09-01 至 1992-10-01
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9114333&HistoricalAwards=false
• 关键词: Strategies; Better; System; Identification

This project will investigate a variety of approaches, to improve the ability of artificial neural networks (ANN) to learn classifications or general mathematical functions. It will investigate alternative functional forms for ANNs, building on the PI's prior work with radial basic functions and B-splines. It will investigate methods for adapting learning rates, based on ideas about stochastic gradient learning theory. It will investigate alternative error functions, beyond the usual square error function, designed to yield better generalization power. Such alterative error function, designed to yield better generalization power. Such alternative error functions may also be used in determining the topology of an ANN.

该项目将研究各种方法，以提高人工神经网络 (ANN) 学习分类或一般数学函数的能力。 它将研究 ANN 的替代函数形式，以 PI 之前的径向基本函数和 B 样条工作为基础。 它将基于随机梯度学习理论的思想，研究调整学习率的方法。 它将研究除通常的平方误差函数之外的替代误差函数，旨在产生更好的泛化能力。 这种替代误差函数旨在产生更好的泛化能力。 这种替代误差函数也可用于确定 ANN 的拓扑。