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

TL;DR

This paper introduces a novel neural network model with a parameterized activation function rooted in fuzzy logic, enabling the discovery of human-understandable feature relationships in classification tasks.

Contribution

It proposes a new differentiable activation function with semantic parameters based on nilpotent fuzzy logic, facilitating interpretable neural models.

Findings

Successfully applied to UCI classification datasets

Demonstrated interpretability of feature relationships

Effective in discovering human-understandable connections

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.