Social and Behavioral Sciences Commons^™

Neural Network Classification And Prior Class Probabilities, Steve Lawrence, Ian Burns, Andrew Back, Ah Chung Tsoi, C Lee Giles

Faculty of Engineering and Information Sciences - Papers: Part A

A commonly encountered problem in MLP (multi-layer perceptron) classification problems is related to the prior probabilities of the individual classes - if the number of training examples that correspond to each class varies significantly between the classes, then it may be harder for the network to learn the rarer classes in some cases. Such practical experience does not match theoretical results which show that MLPs approximate Bayesian a posteriori probabilities (independent of the prior class probabilities). Our investigation of the problem shows that the difference between the theoretical and practical results lies with the assumptions made in the theory (accurate …