计算机科学 ›› 2008, Vol. 35 ›› Issue (4): 252-254.

• • 上一篇    下一篇

基于整合思想的神经网络泛化能力改进研究

黄宏涛   

  1. 广东财经职业学院信息管理系,广州510420
  • 出版日期:2018-11-16 发布日期:2018-11-16

HUANG Hong-Tao (Information Management Department,Guangdong Finance and Economics College,Guangzhou 510420)   

  • Online:2018-11-16 Published:2018-11-16

摘要: 神经网络的泛化能力是影响其可用性的重要方面。本文在总结现有泛化能力改进措施的基础上,将各种独立的改进措施进行了整合,并融入神经网络的构造和训练过程,提出了基于整合思想的神经网络泛化能力改进措施,并针对其中的一类重要问题——确定训练时间进行了具体的数理分析,得出了一些有价值的结论。

关键词: 神经网络 泛化 整合 训练时间

Abstract: Generation capacity of neutral network is the important facet impacting on its usability. In this essay, many separate modified measures are conformed and the process of constitution and training of neutral network is fashioned. This essay makes an analys

Key words: Neutral network, Generation, Conformity, Training time

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!