# Uninorm-like parametric activation functions for human-understandable neural models

arXiv: https://arxiv.org/abs/2205.06547 · HTML: https://mlsanity.com/paper/2205.06547/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 46 references that are in the map.
- First posted on arXiv 13 May 2022.

## Builds on (most cited first, 4 of 4)

- [Interpretable neural networks based on continuous-valued logic and multicriteria decision operators](https://mlsanity.com/paper/1910.02486/) (2019)
- [A parameterized activation function for learning fuzzy logic operations in deep neural networks](https://mlsanity.com/paper/1708.08557/) (2017)
- [Squashing activation functions in benchmark tests: towards eXplainable Artificial Intelligence using continuous-valued logic](https://mlsanity.com/paper/2010.08760/) (2020)
- [Identification of Nonlinear Dynamic Systems Using Type-2 Fuzzy Neural Networks -- A Novel Learning Algorithm and a Comparative Study](https://mlsanity.com/paper/2104.01713/) (2021)

## Abstract (arXiv)

We present a deep learning model for finding human-understandable connections between input features. Our approach uses a parameterized, differentiable activation function, based on the theoretical background of nilpotent fuzzy logic and multi-criteria decision-making (MCDM). The learnable parameter has a semantic meaning indicating the level of compensation between input features. The neural network determines the parameters using gradient descent to find human-understandable relationships between input features. We demonstrate the utility and effectiveness of the model by successfully applying it to classification problems from the UCI Machine Learning Repository.