# Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition

arXiv: https://arxiv.org/abs/2506.22443 · HTML: https://mlsanity.com/paper/2506.22443/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 7 of 7)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [True to the Model or True to the Data?](https://mlsanity.com/paper/2006.16234/) (2020)
- [Learning Accurate and Interpretable Decision Rule Sets from Neural Networks](https://mlsanity.com/paper/2103.02826/) (2021)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Gesture Recognition for FMCW Radar on the Edge](https://mlsanity.com/paper/2310.08876/) (2023)
- [Interpretable Rule-Based System for Radar-Based Gesture Sensing: Enhancing Transparency and Personalization in AI](https://mlsanity.com/paper/2410.12806/) (2024)

## Built on by (most cited first, 1 of 1)

- [GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series](https://mlsanity.com/paper/2509.20936/) (2025)

## Abstract (arXiv)

Rule-based models offer interpretability but struggle with complex data, while deep neural networks excel in performance yet lack transparency. This work investigates a neuro-symbolic rule learning neural network named RL-Net that learns interpretable rule lists through neural optimization, applied for the first time to radar-based hand gesture recognition (HGR). We benchmark RL-Net against a fully transparent rule-based system (MIRA) and an explainable black-box model (XentricAI), evaluating accuracy, interpretability, and user adaptability via transfer learning. Our results show that RL-Net achieves a favorable trade-off, maintaining strong performance (93.03% F1) while significantly reducing rule complexity. We identify optimization challenges specific to rule pruning and hierarchy bias and propose stability-enhancing modifications. Compared to MIRA and XentricAI, RL-Net emerges as a practical middle ground between transparency and performance. This study highlights the real-world feasibility of neuro-symbolic models for interpretable HGR and offers insights for extending explainable AI to edge-deployable sensing systems.