SHADOW TARGETS - A NOVEL ALGORITHM FOR TOPOGRAPHIC PROJECTIONS BY RADIAL BASIS FUNCTIONS

The archetypal neural network topographic paradigm, Kohonen's self-org anising map, has proven highly effective in many applications but neve rtheless has significant disadvantages which can limit its utility. Al ternative feed-forward neural network approaches, including a model ca lled ''NEUROSCALE'', have recently been developed based on explicit di stance-preservation criteria. Excellent generalisation properties have been observed for such models, and recent analysis indicates that suc h behaviour is relatively insensitive to model complexity. As such, it is important that the training of such networks is performed efficien tly, as computation of error and gradients scales in the order of the square of the number of patterns to be mapped. We therefore detail and demonstrate a novel training algorithm for NEUROSCALE which outperfor ms present approaches. (C) 1998 Elsevier Science B.V. All rights reser ved.