Code for the NLDB 2023 paper. Work partially funded by grant ANR-19-CE38-0011-03 from the French national research agency (ANR).

We've developed a powerful binary dog and cat image classifier, driven by advanced deep learning techniques, and enhanced its transparency using Local Interpretable Model-agnostic Explanations (LIME). Witness the magic as the model accurately predicts dog and cat images while LIME reveals the intricate decision-making process behind each result.

XMLX GitHub configuration

El proyecto se centra en la destilación de conocimiento y técnicas de explicabilidad para mejorar el rendimiento de redes neuronales en imágenes naturales.

A curated list of explainability-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights into the explainability implications, challenges, and advancements surrounding these powerful models.

One of the firsts dataset level explanability libraries for 1d signal using GRAD-CAM++

Awesome Heart Sound Analysis - A Survey

This repository is associated with interpretable/explainable ML model for liquefaction potential assessment of gravelly soils. This model is developed using LightGBM and SHAP.

A curated list of awesome contrastive explanation in ML resources

Evaluation framework for post hoc explanation methods | Explainable AI (XAI)

Graduate research project in computer vision and deep learning explainability

This is a list of awesome prototype-based papers for explainable artificial intelligence.

Repository for Kubach et al. bioRxiv/2019/804682 (2019)

[ 공모전 ] 코트라 데이터활용 빅데이터 분석 경진대회

Master's Thesis (Master's Degree in Artificial Intelligence and Robotics at Sapienza University of Rome) - 2023

SG-CF Shapelet-Guided Counterfactual Explanation for Time Series Data (2022 Big Data)

Endocrine Disruption Explainer is a code to generate structural alerts of endocrine disruption of chemcial compounds using Local Interpretable Model-Agnostic Explanations (LIME) of machine learning models from TOX-21, EDC, and EDKB-FDA datasets.

🤖 Making AI understandable and transparent, enhancing trust and accountability.

A more interpretable way to regularize convolutional neural networks (CNNs) during training