# Taxonomic Networks: A Representation for Neuro-Symbolic Pairing

arXiv: https://arxiv.org/abs/2505.24601 · HTML: https://mlsanity.com/paper/2505.24601/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 15 of 15)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [From Statistical Relational to Neuro-Symbolic Artificial Intelligence](https://mlsanity.com/paper/2003.08316/) (2020)
- [NBDT: Neural-Backed Decision Trees](https://mlsanity.com/paper/2004.00221/) (2020)
- [Convolutional Cobweb: A Model of Incremental Learning from 2D Images](https://mlsanity.com/paper/2201.06740/) (2022)
- [Efficient Induction of Language Models Via Probabilistic Concept Formation](https://mlsanity.com/paper/2212.11937/) (2022)
- [Deep Sparse Coding for Invariant Multimodal Halle Berry Neurons](https://mlsanity.com/paper/1711.07998/) (2017)
- [Incremental Concept Formation over Visual Images Without Catastrophic Forgetting](https://mlsanity.com/paper/2402.16933/) (2024)
- [Autoencoder Trees](https://mlsanity.com/paper/1409.7461/) (2014)
- [Cobweb: An Incremental and Hierarchical Model of Human-Like Category Learning](https://mlsanity.com/paper/2403.03835/) (2024)
- [MobilePTX: Sparse Coding for Pneumothorax Detection Given Limited Training Examples](https://mlsanity.com/paper/2212.03282/) (2022)
- [Incremental and Data-Efficient Concept Formation to Support Masked Word Prediction](https://mlsanity.com/paper/2409.12440/) (2024)

## Built on by (most cited first, 4 of 4)

- [Hierarchical Semantic Retrieval with Cobweb](https://mlsanity.com/paper/2510.02539/) (2025)
- [Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation](https://mlsanity.com/paper/2510.23756/) (2025)
- [CobwebTM: Probabilistic Concept Formation for Lifelong and Hierarchical Topic Modeling](https://mlsanity.com/paper/2604.14489/) (2026)
- [Diffusion Models and Concept Formation](https://mlsanity.com/paper/2609.13047/) (2026)

## Abstract (arXiv)

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.