Taxonomic Networks: A Representation for Neuro-Symbolic Pairing
This work provides a foundational representation for future neuro-symbolic AI systems, addressing the integration challenge for researchers in AI and machine learning.
The paper tackles the problem of integrating neural and symbolic approaches by introducing neuro-symbolic pairs linked through taxonomic networks, showing that the symbolic method learns more efficiently with less data and compute, while the neural method achieves higher accuracy with greater resources.
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.