Exploiting Temporal Binding to Learn Relational Rules Within a Connectionist Network

TitleExploiting Temporal Binding to Learn Relational Rules Within a Connectionist Network
Publication TypeTechnical Report
Year of Publication1997
AuthorsShastri, L.
Other Numbers1070
Abstract

Rules encoded by traditional rule-based systems are brittle and inflexible because it is difficult to specify the precise conditions under which a rule should fire. If the conditions are made too specific a rule does not always fire when it should. If the conditions are made too general, the rule fires even when it should not. In contrast, connectionist networks are considered to be capable of learning soft and robust rules. Work in connectionist learning however, has focused primarily on classification and feature formation, and the problem of learning rules involving relations and roles (variables) has received relatively little attention. We present a simple demonstration of rule learning involving relations and variables within a connectionist network. The network learns the appropriate correspondence between roles of antecedent and consequent relations as well as the features that role fillers must possess for a rule to be applicable in a given situation. Each rule can be viewed as a mapping from the symbolic level to the symbolic level mediated by a semantic filter embedded within a subsymbolic level. The network uses synchronous firing of nodes to express dynamic bindings.Key Words: learning; rules; first-order rules; bindings; synchrony; relational rules

URLhttp://www.icsi.berkeley.edu/ftp/global/pub/techreports/1997/tr-97-003.pdf
Bibliographic Notes

ICSI Technical Report TR-97-003

Abbreviated Authors

L. Shastri

ICSI Publication Type

Technical Report