Experiments on machine learning explainability
-
Updated
Mar 26, 2021 - Jupyter Notebook
Experiments on machine learning explainability
Feature assessment and importance of Machine Learning Models using SHAP and CXPlain libraries
Chest X-Ray Images (Pneumonia) classification: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia
Repository for the Linkit Beginner Challenge on Explainable ML using SHAP values.
A method for conditional shapley value estimation, built off the shapr package: https://github.com/NorskRegnesentral/shapr/tree/master
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.
A Team Project on developing COVID-19 predictor with chest X-Ray images as dataset under Data Science with R subject of Otto-von-Guericke-University, Magdeburg
Contribution to the PatchCamelyon Challenge (semester project in image processing)
Repository containing sample datasets, models and notebooks to start using EXPAI.
Python functions to compute and plot global effects from ML models
Strategies to interpret Deep Learning & Machine Learning models/black box; help us to understand how it’s making predictions/decisions.
Graduate research project in computer vision and deep learning explainability
explainable and interpretable methods for AI and data science
Geometry shapes discoverer algorithm based on Explainable AI(xAI)
Streamlit App to inspect Black Box Models
Data Science Examples
Adaptation of the official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks [CVPR 2021] to ESM.
Implementing algorithms based on the analysis of the gradients in NN computational graphs to provide nice insights for Explainable AI
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."