Taxonomic Networks: A Representation for Neuro-Symbolic Pairing

TL;DR

This paper introduces taxonomic networks as a new knowledge representation linking neural and symbolic methods, enabling efficient learning and high accuracy in taxonomic tasks, and facilitating seamless integration of both approaches.

Contribution

The paper presents a novel neuro-symbolic pairing using taxonomic networks, demonstrating their efficiency and accuracy advantages and enabling flexible interchangeability between neural and symbolic methods.

Findings

Symbolic methods learn taxonomic nets more efficiently with less data.

Neural methods achieve higher accuracy with more resources.

The neuro-symbolic pair allows seamless translation between approaches.

Abstract

We introduce the concept of a \textbf{neuro-symbolic pair} -- neural and symbolic approaches that are linked through a common knowledge representation. Next, we present \textbf{taxonomic networks}, a type of discrimination network in which nodes represent hierarchically organized taxonomic concepts. Using this representation, we construct a novel neuro-symbolic pair and evaluate its performance. We show that our symbolic method learns taxonomic nets more efficiently with less data and compute, while the neural method finds higher-accuracy taxonomic nets when provided with greater resources. As a neuro-symbolic pair, these approaches can be used interchangeably based on situational needs, with seamless translation between them when necessary. This work lays the foundation for future systems that more fundamentally integrate neural and symbolic computation.