Learning and Forgetting Surface Classifications with Dynamic Neural Networks

ICANN '93, Amsterdam, The Netherlands, September 13-16, 1993

Herman Keuchel, Ewald von Puttkamer & Uwe R. Zimmer

This paper refers to the problem of adaptability over an infinite period of time, regarding dynamic networks. A never ending flow of examples have to be clustered, based on a distance-measure. The developed model is based on the self-organizing feature maps of Kohonen and some adaptations by Fritzke. The problem of dynamic surface classification is embedded in the SPIN project, where sub-symbolic abstractions, based on a 3-d scanned environment is being done.

Paper (pdf) | Paper (ps.Z) | other publications