Abstract
A connectionist architecture is outlined which makes use of RAAM to generate representations for objects in inheritance networks and extended learning to make such representations context-sensitive. The architecture embodies inheritance quite differently by relying on associative similarities and regions in representational space. The model avoids many of the problems identified for traditional inheritance.
Preview
Unable to display preview. Download preview PDF.
References
M. Bodén. Representing and Reasoning with Nonmonotonic Inheritance Structures using Context-sensitive Connectionist Representations. PhD thesis, University of Exeter, United Kingdom, 1996. In preparation.
M. Bodén and L. Niklasson. Features of distributed representations for tree-structures: A study of RAAM. In Current Trends in Connectionism — Proceedings of the 1995 Swedish Conference on Connectionism, pages 121–140, 1995. LEA.
J. B. Pollack. Recursive distributed representations. Artificial Intelligence, (46):77–105, 1990.
N. E. Sharkey and S. Jackson. An internal report for connectionists. In R. Sun and L. Bookman, editors, Computational architectures integrating neural and symbolic processes, pages 223–44. Kluwer Academic Press, 1994.
D. S. Touretzky, J. F. Horty, and R. H. Thomason. A clash of intuitions: The current state of nonmonotonic multiple inheritance systems. In Proceedings of IJCAI 87, 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bodén, M. (1996). A connectionist variation on inheritance. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_62
Download citation
DOI: https://doi.org/10.1007/3-540-61510-5_62
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61510-1
Online ISBN: 978-3-540-68684-2
eBook Packages: Springer Book Archive