Title :
Effects of the sample size in artificial neural network classifier design
Author :
Uchimura, Shunji ; Hamamoto, Yoshihiko ; Tomita, Shingo
Author_Institution :
Oshima Nat. Coll. of Maritime Technol., Japan
Abstract :
Discusses the effects of the sample size on the estimates of the error rate of the artificial neural network (ANN) classifiers. Experimental results show that the standard deviation of the estimated error rate of ANN classifiers is independent of the hidden unit size. In addition, it is shown that nevertheless the class distributions are Gaussian, ANN classifiers outperform the quadratic discriminant function when sizes of samples per class are much unequal
Keywords :
Gaussian distribution; neural nets; pattern classification; probability; statistical analysis; artificial neural network classifier design; class distributions; error rate; estimated error rate; sample size; standard deviation; Artificial neural networks; Design engineering; Educational institutions; Electronic mail; Error analysis; Intelligent networks; Neural networks; Pattern recognition; Performance analysis; Testing;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.489006
