Abstract
摘要: 本文研究了基于变精度粗糙集模型下的粗集神经网络设计,对近似约简条件进行了弱化推广,同时提出了近似约简的选取原则。在对Brodatz纹理图像的分类实验中,比较了经典粗集神经网络RNN和变精度粗集神经网络VPRNN的性能,VPRNN不仅具有更为精简的结构和更短的训练时间,而且具有更强的近似决策和泛化能力。 关键词: 变精度粗糙集; 粗集神经网络; 近似约简; 纹理分类
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: JOURNAL OF ELECTRONICS INFORMATION & TECHNOLOGY
Paper Title
Journal
Date
