Graduate research project in computer vision and deep learning explainability
-
Updated
Jun 19, 2023 - Python
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
Chest X-Ray Images (Pneumonia) classification: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia
Research project on generation of counterfactuals for eXplainable AI, based on Bayesian Generation
Code for the paper Tětková et al.: Knowledge Graphs for Empirical Concept Retrieval (accepted to The 2nd World Conference on eXplainable Artificial Intelligence).
Explain and interpret predictions of tree-based machine learning models
Python functions to compute and plot global effects from ML models
A Toolbox for the Evaluation of machine learning Explanations
Evaluation of Perturbation Methods for Deep Learning Explanation Methods
Streamlit App to inspect Black Box Models
Implementation of the paper "Preliminary Study on the Impact of Attention Mechanisms for Medical Image Classification" by Tiago Gonçalves and Jaime S. Cardoso.
Chiral version of the MinHashed Atom-Pair Fingerprint
Automating the generation of human readable descriptions of arbitrary subsets of molecular space.
Understanding Morphosyntactic Representations in Pretrained Language Models.
A PyTorch implementation of constrained optimization and modeling techniques
What factors influence the predictions of Deep learning Algorithms?
ExplainPolySVM is a python package to provide interpretation and explainability to Support Vector Machine models trained with polynomial kernels. The package can be used with any SVM model as long as the components of the model can be extracted.
Implementation of Model-Agnostic Graph Explainability Technique from Scratch in PyTorch
Tool to explain Entity Resolution model predictions
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."