Representation and training of vector graphics with NRAAM networks

Author

Schaefer, Mark ; Dilger, Wemer

Author_Institution

Chemnitz Univ. of Technol., Germany

Volume

1

fYear

2003

fDate

20-24 July 2003

Firstpage

473

Abstract

Recursive auto-associative memory networks (RAAM) are neural networks that can be trained to represent structured information. After training, this information can be retrieved following its inner structure. By now, RAAM networks were applied only to syntactical expressions like parse trees of natural language sentences or logical terms. In this paper it is shown how they can be used for representing vector graphics that are given as a tree. For this purpose we developed name RAAM networks (NRAAM) which are more suitable for the training of complex information than normal RAAMs.

Keywords

computer graphics; content-addressable storage; feedforward neural nets; knowledge representation; learning (artificial intelligence); multilayer perceptrons; trees (mathematics); complex information; inner structure; logical terms; natural language sentences; neural network; parse trees; recursive autoassociative memory network; structured information; syntactical expression; vector graphic; Chemical technology; Concrete; Decoding; Feedforward systems; Graphics; Natural languages; Neural networks; Neurons; Tree graphs;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2003. Proceedings of the International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7898-9

Type

conf

DOI

10.1109/IJCNN.2003.1223392

Filename

1223392