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

Autor:	Csiszár, Orsolya, Pusztaházi, Luca Sára, Dénes-Fazakas, Lehel, Gashler, Michael S., Kreinovich, Vladik, Csiszár, Gábor
Rok vydání:	2022
Předmět:	Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2205.06547 Zobrazit plný text záznamu View this record from Arxiv