Network Complexity and Generalization Performance of Large Function Approximating Neural Networks

大函数逼近神经网络的网络复杂性和泛化性能

• 批准号: 9312504
• 负责人: Chuanyi Ji
• 金额: $ 10.64万
• 依托单位: Rensselaer Polytechnic Institute
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1993
• 资助国家: 美国
• 起止时间: 1993-09-01 至 1997-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9312504&HistoricalAwards=false
• 关键词: Network; Complexity; Generalization; Performance; Large

Ji 9312504 This research will address an important open problem in supervised learning using feedforward multi-layer neural networks: how to evaluate generalization performance of the networks using network-parameter-dependent information. The focus is on large networks used for the purpose of function approximation. The objectives are: 1) to evaluate the generalization error utilizing the network-parameter-dependent information; 2) to incorporate dynamics of training algorithms into evaluation of generalization error; 3) to design network complexity in order to achieve more predictable generalization on a small training set for large networks with fixed architecture. To achieve these objectives, statistical methods will be used to develop a general relationship between the generalization error and the expected network complexity. And a Bayesian network is utilized to relate dynamics of training algorithms to the generalization performance of the networks. The impact of the proposed research is to important open problems in combined supervised and reinforcement learning, and high-speed high-capacity large optical neural networks. *** v s t APPS HLP @ j N= ARGYLE BMP @ j o v CARS BMP @ j p v CHARMAP EXE @ j q V CHORD WAV @ j | a EXPAND EXE @ j ; FLOCK BMP @ j ^ GLOSSARYHLP @ j MPLAYER HLP @ j `2 NETWORKSWRI @ j NOTEPAD EXE @ j Ji 9312504 This research will address an important open problem in supervised learning using feedforward mul ti-layer neural ne $ $ ( F / / 1 Courier Symbol & Arial 5 Courier New " h % % * V R:\WW20USER\ABSTRACT.DOT ji abstract Alicia E. Harris Alicia E. Harris

Ji 9312504本研究将解决使用前馈多层神经网络的监督学习中的一个重要的开放问题：如何使用网络参数相关信息来评估网络的泛化性能。 重点是用于函数逼近的大型网络。 目标是：1）利用网络参数相关信息评估泛化误差; 2）将训练算法的动态性纳入泛化误差评估; 3）设计网络复杂度，以便在具有固定结构的大型网络的小训练集上实现更可预测的泛化。 为了实现这些目标，将使用统计方法来开发泛化误差和预期网络复杂性之间的一般关系。 利用贝叶斯网络将训练算法的动态性与网络的泛化性能联系起来。 所提出的研究的影响是重要的开放问题相结合的监督和强化学习，高速大容量的大型光学神经网络。 *** v S t 应用程序 HLP @ j N=阿盖尔BMP @ jo v 汽车 BMP @ jp v CHARMAP EXE @ j q V CHORD WAV @ j|扩展EXE @ j ; FLOCK BMP @ j ^ GLOSSALYHLP @ j MPLAYER HLP @ j `2网络工作 @ j 记事本EXE @ j JI 9312504这项研究将解决一个重要的开放问题，在监督学习使用前馈穆尔神经网络 $ $ ( F / / 1件 Symbol Arial 5 Cash New " H % % * V R：\WW20USER\ABSTRACT.DOT ji摘要 艾丽西娅·E哈里斯·艾丽西娅·E.哈里斯