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.
HS-IDA-TR-96-015. International Conference on Artificial Neural Networks ICANN 1996: Artificial Neural Networks — ICANN 96 pp 353-358. Part of the Lecture Notes in Computer Science book series (LNCS, volume 1112). "The Connectionist Research Group, Comp. Sci. Dept. University of Skövde Sweden"