Learning Topology-Preserving Maps Using Self-Supervised Backpropagation on a Parallel Machine
Title | Learning Topology-Preserving Maps Using Self-Supervised Backpropagation on a Parallel Machine |
Publication Type | Technical Report |
Year of Publication | 1992 |
Authors | Ossen, A. |
Other Numbers | 764 |
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). |
URL | http://www.icsi.berkeley.edu/ftp/global/pub/techreports/1992/tr-92-059.pdf |
Bibliographic Notes | ICSI Technical Report TR-92-059 |
Abbreviated Authors | A. Ossen |
ICSI Publication Type | Technical Report |