MOUSE-CHROMOSOME CLASSIFICATION BY RADIAL BASIS FUNCTION NETWORK WITHFAST ORTHOGONAL SEARCH

This paper provides the results of our study on automatic classificati on of mouse chromosomes. A radial basis function neural network was co mpared with a multi-layer perceptron and a probabilistic neural networ k. The networks were trained and tested with 3723 chromosomes presente d to each network as 30-point banding profiles. The radial basis funct ion classifier trained with the fast orthogonal search learning rule p rovided the best unconstrained classification error rate of 12.7% whic h was obtained with a training set of 2250 chromosomes. (C) 1998 Elsev ier Science Ltd. All rights reserved.