文章基本信息

标题：Determination of Over-Learning and Over-Fitting Problem in Back Propagation Neurl Network
本地全文：下载
作者：Gaurang Panchal ; Amit Ganatra ; Parth Shah 等
期刊名称：International Journal on Soft Computing
电子版ISSN：2229-7103
出版年度：2011
卷号：2
期号：2
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：A drawback of the error-back propagation algorithm for a multilayer feed forward neural network is over learning or over fitting. We have discussed this problem, and obtained necessary and sufficient Experiment and conditions for over-learning problem to arise. Using those conditions and the concept of a reproducing, this paper proposes methods for choosing training set which is used to prevent over-learning. For a classifier, besides classification capability, its size is another fundamental aspect. In pursuit of high performance, many classifiers do not take into consideration their sizes and contain numerous both essential and insignificant rules. This, however, may bring adverse situation to classifier, for its efficiency will been put down greatly by redundant rules. Hence, it is necessary to eliminate those unwanted rules. We have discussed various experiments with and without over learning or over fitting problem.
关键词：Neural Network; learning; Hidden Neurons; Hidden Layers