Analysis and Training of Neural Networks Using Voronoi Diagrams and Graph Decomposition

使用 Voronoi 图和图分解来分析和训练神经网络

• 批准号: 9114997
• 负责人: Nirmal Bose
• 金额: $ 3.58万
• 依托单位: Pennsylvania State Univ University Park
• 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 1993-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9114997&HistoricalAwards=false
• 关键词: Analysis; Training; Neural; Networks; Using

This proposal presents a novel solution to the multilayer neural network training problem - determining the connection weights of the neurons - using a very powerful construct from combinatorial geometry called a Voronoi diagram. It will also address the equally important problem of how to partition a neural network into smaller subnetworks which can then be used either individually or together to approximate the function of the original network.

这一建议提出了一种新的解决方案，多层神经网络 网络训练问题-确定连接权重 神经元-使用一个非常强大的结构， 称为Voronoi图的几何学。 它还将解决 同样重要的问题是如何将神经网络划分为 较小的子网，然后可以单独使用， 一起来近似原始网络的功能。