Part of Advances in Neural Information Processing Systems 5 (NIPS 1992)
A performance comparison of two self-organizing networks, the Ko(cid:173) honen Feature Map and the recently proposed Growing Cell Struc(cid:173) tures is made. For this purpose several performance criteria for self-organizing networks are proposed and motivated. The models are tested with three example problems of increasing difficulty. The Kohonen Feature Map demonstrates slightly superior results only for the simplest problem. For the other more difficult and also more realistic problems the Growing Cell Structures exhibit significantly better performance by every criterion . Additional advantages of the new model are that all parameters are constant over time and that size as well as structure of the network are determined auto(cid:173) matically.