Uninorm-like parametric activation functions for human-understandable neural models
Artificial Intelligence
2022-05-16 v1 Machine Learning
Abstract
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.
Keywords
Cite
@article{arxiv.2205.06547,
title = {Uninorm-like parametric activation functions for human-understandable neural models},
author = {Orsolya Csiszár and Luca Sára Pusztaházi and Lehel Dénes-Fazakas and Michael S. Gashler and Vladik Kreinovich and Gábor Csiszár},
journal= {arXiv preprint arXiv:2205.06547},
year = {2022}
}