Explainable AI in Julia.

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

Repository for the journal article 'SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology prediction'

xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology

This repository contains the code to generate the questionnaire that was conducted for the sake of our paper *Labarta et al.: Study on the Helpfulness of Explainable Artificial Intelligence (2024)* as well as the scripts for the analysis of the gathered survey results.

Repository for the 'best student paper award' winning paper at the IEEE 35th International Symposium on Computer Based Medical Systems (CBMS 2022), Exploring LRP and Grad-CAM visualization to interpret multi-label-multi-class pathology prediction using chest radiography, Mahbub Ul Alam, Jón Rúnar Baldvinsson and Yuxia Wang. https://doi.org/10.11…

Implementation or LRP and Object detection on Brain scans to detect Brain Tumor and Alzhimers

We predict religion from personal names only.

Explainability of Deep RL algorithms using graph networks and layer-wise relevance propagation.

An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization

ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs

Cyber Security AI Dashboard

An XAI library that helps to explain AI models in a really quick & easy way

A utility for generating heatmaps of YOLOv8 using Layerwise Relevance Propagation (LRP/CRP).

(Master's Thesis) Alam, Mahbub Ul, From Speech to Image: A Novel Approach to Understand the Hidden Layer Mechanisms of Deep Neural Networks in Automatic Speech Recognition, Masterarbeit, Institut für Maschinelle Sprachverarbeitung, Universität Stuttgart, 2017. (https://www.ims.uni-stuttgart.de/en/research/publications/theses/)

Code used in paper 'Comprehensive social trait judgments from faces in autism spectrum disorder'

[ECCV 2022: Oral] In this work, we discover that color is a crtical transferable forensic feature (T-FF) in universal detectors for detecting CNN-generated images.

eirspo official branch of odoo for better localization and openness

A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.

Explain Neural Networks using Layer-Wise Relevance Propagation and evaluate the explanations using Pixel-Flipping and Area Under the Curve.