Examples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.

📍 Interactive Studio for Explanatory Model Analysis

💡 Adversarial attacks on explanations and how to defend them

Boosting the AI research efficiency

Implements the Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, Weighted Tsetlin Machine, and Embedding Tsetlin Machine, with support for continuous features, multigranularity, clause indexing, and literal budget

Pytorch implementation of various neural network interpretability methods

Mechanistically interpretable neurosymbolic AI (Nature Comput Sci 2024): losslessly compressing NNs to computer code and discovering new algorithms which generalize out-of-distribution and outperform human-designed algorithms

SurvSHAP(t): Time-dependent explanations of machine learning survival models

Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.

Code for Interpretable Adversarial Perturbation in Input Embedding Space for Text, IJCAI 2018.

This code repository is associated with the paper "A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography." Nature Machine Intelligence, 2021. https://www.nature.com/articles/s42256-021-00423-x

This repo contains code for Invariant Grounding for Video Question Answering

Summarization of static graphs using the Minimum Description Length principle

Techniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.

graph neural networks, information theory, AI for Sciences

Trustworthy LoS Prediction Based on Multi-modal Data (AIME 2023)

Framework for material structure exploration

Explainable Boosting Machines

Visual explanations of supervised classification models

Maximal Linkability metric to evaluate the linkability of (protected) biometric templates. Paper: "Measuring Linkability of Protected Biometric Templates using Maximal Leakage", IEEE-TIFS, 2023.