PIP-Net: Patch-based Intuitive Prototypes Network for Interpretable Image Classification (CVPR 2023)

Fixes 500+ mislabeled MURA images

Always sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to b…

ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021

A Python implementation of global optimization with gaussian processes.

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Implementation of Conditional Neural Networks in Pytorch.

PMLB: A large, curated repository of benchmark datasets for evaluating supervised machine learning algorithms.

Code and documentation for experiments in the TreeExplainer paper

Code for AAAI 2018 accepted paper: "Beyond Sparsity: Tree Regularization of Deep Models for Interpretability"

Latex code for making neural networks diagrams

Interpreting CNN Knowledge via an Explanatory Graph

Uniform Manifold Approximation and Projection

Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University