# NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks

arXiv: https://arxiv.org/abs/2110.02775 · HTML: https://mlsanity.com/paper/2110.02775/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 5 Oct 2021.

## Builds on (most cited first, 10 of 10)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons](https://mlsanity.com/paper/1811.03233/) (2018)
- [What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models](https://mlsanity.com/paper/1812.09355/) (2018)
- [A Survey of Optimization Methods from a Machine Learning Perspective](https://mlsanity.com/paper/1906.06821/) (2019)
- [A survey on modern trainable activation functions](https://mlsanity.com/paper/2005.00817/) (2020)
- [Deep Neural Decision Trees](https://mlsanity.com/paper/1806.06988/) (2018)
- [Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks](https://mlsanity.com/paper/1904.00605/) (2019)
- [NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks](https://mlsanity.com/paper/1812.09359/) (2018)
- [A New Type of Neurons for Machine Learning](https://mlsanity.com/paper/1704.08362/) (2017)

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

- [GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations](https://mlsanity.com/paper/2208.04222/) (2022)

## Abstract (arXiv)

In this work, we formulate NEWRON: a generalization of the McCulloch-Pitts neuron structure. This new framework aims to explore additional desirable properties of artificial neurons. We show that some specializations of NEWRON allow the network to be interpretable with no change in their expressiveness. By just inspecting the models produced by our NEWRON-based networks, we can understand the rules governing the task. Extensive experiments show that the quality of the generated models is better than traditional interpretable models and in line or better than standard neural networks.