A symbolic-connectionist theory of relational inference and generalization.

TLDR

The authors propose a psychologically realistic theory of relational inference and generalization, instantiated in the LISA simulation model. The mechanism is a symbolic connectionist system that uses distributed concept representations, temporal synchrony for binding, and self‑supervised learning to infer relations and acquire new schemas. The model successfully simulates empirical phenomena of analogical inference and relational generalization, demonstrating its sufficiency.

Abstract

The authors present a theory of how relational inference and generalization can be accomplished within a cognitive architecture that is psychologically and neurally realistic. Their proposal is a form of symbolic connectionism: a connectionist system based on distributed representations of concept meanings, using temporal synchrony to bind fillers and roles into relational structures. The authors present a specific instantiation of their theory in the form of a computer simulation model, Learning and Inference with Schemas and Analogies (LISA). By using a kind of self-supervised learning, LISA can make specific inferences and form new relational generalizations and can hence acquire new schemas by induction from examples. The authors demonstrate the sufficiency of the model by using it to simulate a body of empirical phenomena concerning analogical inference and relational generalization.