You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This repository introduces different Explainable AI approaches and demonstrates how they can be implemented with PyTorch and torchvision. Used approaches are Class Activation Mappings, LIMA and SHapley Additive exPlanations.
This notebook can be downloaded, tested and modified with Google Colab and aims at explainable how a Decision Tree is built. It is also coupled with a Medium article.
Methods to improve the explainability of machine learning models, while still being performant models. This repository presents an implementation of Google Brain's Team Distilling a neural network into a Soft Decision Tree by Nicholas Frosst and Geoffrey Hinton.
This notebook is ispired by the AIX360 HELOC Credit Approval Tutorial, which shows different explainability methods for a credit approval process. Here XGBoost is used for classification, achieving better accuracy than most of the models used in that notebook. Then, feature importance methods are shown, to be compared with the Data Scientist exp…
A Bachelor's Thesis project analyzing and comparing classifiers for breast cancer detection using fine needle aspiration biopsies. Includes Jupyter Notebooks for model training and evaluation, and a LaTeX document detailing the methodology and results. Features SHAP for explainable AI analysis.
This repo contains code for predicting life satisfaction using machine learning and explainable AI, as published in Heliyon. It includes a Jupyter Notebook with data processing, model building, and result visualization using Python libraries. The analysis uses the SHILD dataset to explore factors influencing life satisfaction.
Collection of notebooks performing analysis of data and visualisations of outputs for a research paper on evaluation of GHG emissions in Burmese reservoirs
This notebook demonstrates a number of saliency mask techniques, augmented with the SmoothGrad technique, using the VGG16, AlexNet, InceptioNet, MobileNet convolutional neural network in TF2.