Learning Topology-Preserving Maps Using Self-Supervised Backpropagation on a Parallel Machine (1992)
BibTeX
@MISC{Parallel92learningtopology-preserving,
author = {Backpropagation On A Parallel and Arnfried Ossen},
title = {Learning Topology-Preserving Maps Using Self-Supervised Backpropagation on a Parallel Machine},
year = {1992}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Self-supervised backpropagation is an unsupervised learning procedure for feedforward networks, where the desired output vector is identical with the input vector. For backpropagation, we are able to use powerful simulators running on parallel machines. Topology-preserving maps, on the other hand, can be developed by a variant of the competitive learning procedure. However, in a degenerate case, self-supervised backpropagation is a version of competitive learning. A simple extension of the cost function of backpropagation leads to a competitive version of self-supervised backpropagation, which can be used to produce topographic maps. We demonstrate the approach applied to the Traveling Salesman Problem (TSP). The algorithm was implemented using the backpropagation simulator (CLONES) on a parallel machine (RAP). International Computer Science Institute, Berkeley !ossen@icsi.berkeley.edu?, and Technische Universit at Berlin, Germany !ao@cs.tu-berlin.de?. ii 1.
Keyphrases
parallel machine topology-preserving map using self-supervised backpropagation self-supervised backpropagation traveling salesman problem simple extension input vector output vector competitive learning procedure competitive learning unsupervised learning procedure topology-preserving map powerful simulator international computer science institute topographic map backpropagation simulator cost function feedforward network technische universit competitive version degenerate case
