Thomas Martinetz and Klaus Schulten.
Topology representing networks.
Neural Networks, 7:507-522, 1994.
MART94A Hebbian adaptation rule with winner-take-all like competition is introduced. It is shown that this competitive Hebbian rule forms so-called Delaunay triangulations, which play an important role in computational geometry for efficiently solving proximity problems. Given a set of neural units i, i = 1, ..., N, the synaptic weights of which can be interpreted as pointers , i = 1, ..., N in , the competitive Hebbian rule leads to a connectivity structure between the units i that corresponds to the Delaunay triangulation of the set of pointers w. Such competitive Hebbian rule develops connections ( > 0) between neural units i, j with neighboring receptive fields (Voronoi polygons) ,, whereas between all other units i, j no connections evolve ( = 0). Combined with a procedure that distributes the pointers over a given feature manifold M, for example, a submanifold M , the competitive Hebbian rule provides a novel approach to the problem of constructing topology preserving feature maps and representing intricately structured manifolds. The competitive Hebbian rule connects only neural units, the receptive fields (Voronoi polygons) , of which are adjacent on the given manifold M. This leads to a connectivity structure that defines a perfectly topology preserving map and forms a discrete, path preserving representation of M, also in cases where M has an intricate topology. This makes this novel approach particularly useful in all applications where neighborhood relations have to be exploited or the shape and topology of submanifolds have to be taken into account.
This document was last
modified on Fri Oct 11 10:32:21 2002
Material on this page is copyrighted
Contact Webmaster for
more information
148129 accesses since 03 Nov 2000