Connectionist networks qua graphs

✍ Scribed by D. Partridge

• Publisher: Elsevier Science
• Year: 1988
• Tongue: English
• Weight: 521 KB
• Volume: 15
• Category: Article
• ISSN: 0898-1221
• DOI: 10.1016/0898-1221(88)90219-2

✦ Synopsis

There is a lot of excitement in the field of artificial intelligence (AI) at the moment centering around the ideas of "connectionism". Connections networks are used to represent knowledge in terms of "subsymbolic" nodes (i.e. a single node does not by itself represent a conceptual entity, such as a dog, apple, Mary; any node may participate in a number of patterns of activation and each such pattern is a representation of a conceptual entity). The edges of these networks are arcs, with an associated numeric weight, whose role is to transfer "activity" from one node to another according to some function of the arc weights. The phenomenon of learning is typically modeled by adjusting arc weights according to some function of the network's desired and observed performance.

The connectionist paradigna is seen as a promising new approach to the realization of intelligent systems, and one that may be particularly amenable to formal analysis. This paper introduces conneetionism, points out some of the major problems and argues that a graph theoretical approach to some of the recognized problems may prove fruitful.

NETWORKS AND KNOWLEDGE REPRESENTATION IN AI