Learning Spatial Concepts Using a Partially-Structured Connectionist Architecture

This paper reports on the learning of spatial concepts in the L0 project. The challenge of designing an architecture capable of learning spatial concepts from any of the world's languages is first highlighted by reviewing the spatial systems of a number of languages which differ strikingly from English in this regard. A partially structured connectionist architecture is presented which has successfully learned concepts from the languages outlined. In this architecture, highly structured subnetworks, specialized for the spatial concept learning task, feed into an unstructured, fully-connected upper subnetwork. The system's success at the learning task is attributed on the one hand to the constrained search space which results from structuring, and on the other hand to the flexibility afforded by the unstructured upper subnetwork.

ICSI Technical Report TR-91-050

Technical Report