- Suche

- Kontakt

Training and Holistic Computation of Vector Graphics with Hebbian Bases in Contrast to RAAM Networks

Mark Schaefer, Werner Dilger
in: Portland, Oregon Proceedings of the International Joint Conference on Neural Networks, 2003
ISBN: 0-7803-7899-7

Hebbian Learning is well-known for training of associative networks whereas RAAM learning uses auto-associative networks which are trained to represent structured information like parse trees of natural sentences or logical terms. In this paper Hebbian learning is used for representing structured information in terms of vector graphic. The resulting networks are holistically computed.  furthermore a theorem relating bipolar Hebbian learning is proved.

Downloads: