Neurally Implementable Semantic Networks

TL;DR

This paper introduces principles for designing semantic networks that can be implemented as neural networks, emphasizing node interpretation, category representation, and relationship implementation without typed links.

Contribution

It presents a novel framework for semantic networks compatible with neural network implementation, focusing on node interpretation and relationship representation.

Findings

Semantic networks can be systematically implemented as neural networks.

Nodes can represent categories, types, and instances effectively.

Relationships can be encoded without intrinsically typed links.

Abstract

We propose general principles for semantic networks allowing them to be implemented as dynamical neural networks. Major features of our scheme include: (a) the interpretation that each node in a network stands for a bound integration of the meanings of all nodes and external events the node links with; (b) the systematic use of nodes that stand for categories or types, with separate nodes for instances of these types; (c) an implementation of relationships that does not use intrinsically typed links between nodes.