References¶

Related academic papers¶

Fidex: An Algorithm for the Explainability of Ensembles and SVMs¶

2024, by Prof. Guido Bologna, Jean-Marc Boutay, Quentin Leblanc & Damian Boquete

A Rule Extraction Technique Applied to Ensembles of Neural Networks, Random Forests, and Gradient-Boosted Trees¶

2021, by Prof. Guido Bologna

A Two-Step Rule-Extraction Technique for a CNN¶

2020, by Prof. Guido Bologna & Silvio Fossati

A Simple Convolutional Neural Network with Rule Extraction¶

2019, by Prof. Guido Bologna

Exploring Internal Representations of Deep Neural Networks¶

2019, by Jérémie Despraz, Stéphane Gomez, Héctor F. Satizábal & Prof. Carlos Andrés Peña-Reyes

Improving neural network interpretability via rule extraction¶

2018, by Stéphane Gomez Schnyder, Jérémie Despraz & Prof. Carlos Andrés Peña-Reyes

A Comparison Study on Rule Extraction from Neural Network Ensembles, Boosted Shallow Trees, and SVMs¶

2018, by Prof. Guido Bologna & Yoichi Hayashi

QSVM: A support vector machine for rule extraction.¶

2015, by Prof. Guido Bologna & Yoichi Hayashi

Elevating the discussion on security management: The data centric paradigm.¶

2007, by Tyrone Grandison, Prof. Marcel Graf et al.

Is it worth generating rules from neural network ensembles?¶

2004, by Prof. Guido Bologna

A model for single and multiple knowledge based networks.¶

2003, by Prof. Guido Bologna

A fuzzy-genetic approach to breast cancer diagnosis¶

1999, by Prof. Carlos Andrés Peña-Reyes & Moshe Sipper

Online resources¶

dimlpfidex GitHub Repository¶

This is the official GitHub repository containing the code for the dimlpfidex algorithms.

mlxplain GitHub Repository¶

This repository contains the mlxplain package, which serves as a comprehensive framework designed to extend the capabilities of OmniXAI.

rules-extraction GitHub Repository¶

This is the official GitHub repository containing the code for the rules-extraction algorithms.

Docker base image for HES-XPLAIN notebooks¶

The Docker base image is built upon the Jupyter Docker Stacks Pytorch image. It includes Jupyter and all dependency packages necessary to run the provided notebooks, while allowing Pytorch operations to use compatible NVIDIA GPUs for accelerated computations.