interpretable-ai

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Fit interpretable models. Explain blackbox machine learning.

Model interpretability and understanding for PyTorch

A curated list of awesome machine learning interpretability resources.

A collection of research materials on explainable AI/ML

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

H2O.ai Machine Learning Interpretability Resources

Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code. We are looking for co-authors to take this project forward. Reach out @ ms8909@nyu.edu

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

Package towards building Explainable Forecasting and Nowcasting Models with State-of-the-art Deep Neural Networks and Dynamic Factor Model on Time Series data sets with single line of code. Also, provides utilify facility for time-series signal similarities matching, and removing noise from timeseries signals.

All about explainable AI, algorithmic fairness and more

XAI in Julia using Flux.

Modular Python Toolbox for Fairness, Accountability and Transparency Forensics

The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification".

XAI based human-in-the-loop framework for automatic rule-learning.

Code for NeurIPS 2019 paper ``Self-Critical Reasoning for Robust Visual Question Answering''

In this part, I've introduced and experimented with ways to interpret and evaluate models in the field of image. (Pytorch)

Explainability of Deep Learning Models

Slides, videos and other potentially useful artifacts from various presentations on responsible machine learning.