Explainable Neural Networks Based on Fuzzy Logic and Multi-criteria Decision Tools

@inproceedings{Dombi2021ExplainableNN,
  title={Explainable Neural Networks Based on Fuzzy Logic and Multi-criteria Decision Tools},
  author={J{\'o}zsef D{\'a}niel Dombi and Orsolya Csisz{\'a}r},
  booktitle={Studies in Fuzziness and Soft Computing},
  year={2021}
}

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

TLDR
The model uses a parameterized, differentiable activation function, based on the theoretical background of nilpotent fuzzy logic and multi-criteria decision-making (MCDM) to form human-understandable connections between input features.

Medical recommender systems based on continuous-valued logic and multi-criteria decision operators, using interpretable neural networks

TLDR
A novel recommender system that uses predicted outcomes based on continuous-valued logic and multi-criteria decision operators that is transparent, safer against adversarial attacks than conventional deep learning methods since it drastically reduces the number of trainable parameters and simulates cognitive processes like a rational, logical thinking process.