COMPARING BP AND ART-II NEURAL-NETWORK CLASSIFIERS FOR FACILITY LOCATION

This paper compares the performance of Artificial Neural Networks (ANN s) as classifiers in the facility location domain. The ART II (Adaptiv e Resonance Theory) and BP (Back Propagation) paradigms are used as ex emplars of ANNs developed using supervised and unsupervised learning. Their performances are compared with that obtained using a linear mult i-attribute utility model (MAUM) to classify the 48 states in the cont inental U.S.A. based on location profiles developed from government pu blications. In this paper, the models are used to classify the U.S. st ates based on their suitability for accommodating new manufacturing fa cilities. For this data set, the BP ANN model displayed robust perform ance and showed better convergence with the MAUM.