Conference proceeding
Taxonomic Networks: A Representation for Neuro-Symbolic Pairing
INTERNATIONAL CONFERENCE ON NEURO-SYMBOLIC SYSTEMS, v 288
01 Jan 2025
Abstract
We introduce the concept of a neuro-symbolic pair-neural and symbolic approaches that are linked through a common knowledge representation. Next, we present 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.
Metrics
1 Record Views
Details
- Title
- Taxonomic Networks: A Representation for Neuro-Symbolic Pairing
- Creators
- Zekun Wang - Georgia Institute of TechnologyEthan L. Haarer - Georgia Institute of TechnologyNicki Barari - Drexel UniversityChristopher J. MacLellan - Georgia Institute of Technology
- Contributors
- G Pappas (Editor)P Ravikumar (Editor)S A Seshia (Editor)
- Publication Details
- INTERNATIONAL CONFERENCE ON NEURO-SYMBOLIC SYSTEMS, v 288
- Series
- Proceedings of Machine Learning Research
- Publisher
- JMLR-JOURNAL MACHINE LEARNING RESEARCH
- Number of pages
- 13
- Grant note
- W911NF2320203 / ARL STRONG Program
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Information Science
- Web of Science ID
- WOS:001595136800024
- Scopus ID
- 2-s2.0-105014734193
- Other Identifier
- 991022197421204721