DETERMINATION OF OVER-LEARNING AND OVER-FITTING PROBLEM IN BACK PROPAGATION NEURAL NETWORK

A drawback of the error-back propagation algorithm for a multilayer feed forward neural network is overlearning or over fitting. We have discussed this problem, and obtained necessary and sufficient Experimentand conditions for over-learning problem to arise. Using those conditions and the concept of areproducing, 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 highperformance, many classifiers do not take into consideration their sizes and contain numerous bothessential and insignificant rules. This, however, may bring adverse situation to classifier, for its efficiencywill 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.