| 本文已被：浏览 11399次 下载 8154次 |
码上扫一扫！ |
|
|
| M-P神经元模型的几何意义及其应用 |
|
张铃1,2, 张钹3,2
|
|
1.安徽大学人工智能研究所,合肥,230039;2.清华大学智能技术与系统国家重点实验室,北京,100084;3.清华大学计算机科学与技术系,北京,100084
|
|
| 摘要: |
| 给出M-P神经元模型的几何意义,这个几何的铨释,给神经元一个非常直观的理解,利用这个直观的理解,给出两个颇为有趣的应用:(1)用此法给出三层前向神经网络的学习能力的基本定理的新的证明;(2)给出前向网络的拓扑结构设计的新方法. |
| 关键词: 前向神经网络,领域覆盖,可测函数. |
| DOI： |
| 分类号: |
| 基金项目:本文研究得到国家自然科学基金、国家863高科技项目基金和国家“攀登”计划基金资助. |
|
| A Geometrical Representation of M-P Neural Model and Its Applications |
|
ZHANG Ling,ZHANG Bo
|
| Abstract: |
| In this paper, a geometrical representation of M-P neural model is presented. From the representation,a clear visual picture and interpretation of the model can be seen. Two interesting applications based on the interpretation are discussed. They are (1) a new design principle of feedforward neural networks, and (2) a new proof of mapping abilities of three-layer feedforward neural networks. |
| Key words: A Geometrical Representation of M-P Neural Model and Its Applications |
