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

Model interpretability and understanding for PyTorch

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

The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification" and TPAMI paper "Learning Interpretable Rules for Scalable Data Representation and Classification"

Material related to my book Intuitive Machine Learning. Some of this material is also featured in my new book Synthetic Data and Generative AI.

Modular Python Toolbox for Fairness, Accountability and Transparency Forensics

Python library to explain Tree Ensemble models (TE) like XGBoost, using a rule list.

SIDU: SImilarity Difference and Uniqueness method for explainable AI

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

Interpretable Pre-Trained Transformers for Heart Time-Series Data

Implementation of Beyond Neural Scaling beating power laws for deep models and prototype-based models

A Multimodal Transformer: Fusing Clinical Notes With Structured EHR Data for Interpretable In-Hospital Mortality Prediction

A PyTorch implementation of constrained optimization and modeling techniques

Explainability of Deep Learning Models

Find the samples, in the test data, on which your (generative) model makes mistakes.

The code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".

[ICCV 2023] Learning Support and Trivial Prototypes for Interpretable Image Classification

ProtoTorch is a PyTorch-based Python toolbox for bleeding-edge research in prototype-based machine learning algorithms.

NAISR: A 3D Neural Additive Model for Interpretable Shape Representation