Experiments on machine learning explainability
-
Updated
Mar 26, 2021 - Jupyter Notebook
Experiments on machine learning explainability
Demo on performing Explainable AI using the SHAP Library
Exploration of ML Explainability Methods on the Statlog (Heart) Data Set
Awesome papers on Interpretable Machine Learning
This repository provides a summarization of recent empirical studies/human studies that measure human understanding with machine explanations in human-AI interactions.
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
Source code of NeurIPS'21 paper: Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach
Binary classification, SHAP (Explainable Artificial Intelligence), and Grid Search (for tuning hyperparameters) using EfficientNetV2-B0 on Cat VS Dog dataset.
Chest X-Ray Images (Pneumonia) classification: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia
Validate the model card document in a GitHub action
Repository for the Linkit Beginner Challenge on Explainable ML using SHAP values.
Binary Classification with Neural Networks and Bayesian Optimization and SHAP Model Explanations
A method for conditional shapley value estimation, built off the shapr package: https://github.com/NorskRegnesentral/shapr/tree/master
Ths repo has the list of Interesting Literature in the domain of XAI
Research project on generation of counterfactuals for eXplainable AI, based on Bayesian Generation
Explaining blackbox predictions using python libraries.
A take on highly imbalanced fraud classification using permutation importance to select top features and explaining the model using SHAP.
Add a description, image, and links to the explainable-ml topic page so that developers can more easily learn about it.
To associate your repository with the explainable-ml topic, visit your repo's landing page and select "manage topics."