ankurtaly / Integrated-Gradients
Attributing predictions made by the Inception network using the Integrated Gradients method
☆593Updated 2 years ago
Related projects: ⓘ
- A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also in…☆727Updated 4 years ago
- This is the pytorch implementation of the paper - Axiomatic Attribution for Deep Networks.☆180Updated 2 years ago
- ☆770Updated 3 years ago
- Public facing deeplift repo☆818Updated 2 years ago
- Code for "High-Precision Model-Agnostic Explanations" paper☆794Updated 2 years ago
- ☆903Updated last year
- Tensorflow tutorial for various Deep Neural Network visualization techniques☆345Updated 4 years ago
- Code for the TCAV ML interpretability project☆628Updated last month
- ☆264Updated 4 years ago
- ☆559Updated last year
- Code for all experiments.☆305Updated 3 years ago
- Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet☆604Updated last year
- This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence…☆314Updated 10 months ago
- Towards Automatic Concept-based Explanations☆154Updated 4 months ago
- Implementations of various VAE-based semi-supervised and generative models in PyTorch☆704Updated 4 years ago
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)☆124Updated 3 years ago
- Interesting resources related to XAI (Explainable Artificial Intelligence)☆816Updated 2 years ago
- Layer-wise Relevance Propagation (LRP) for LSTMs.☆220Updated 4 years ago
- A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.☆546Updated 7 months ago
- The LRP Toolbox provides simple and accessible stand-alone implementations of LRP for artificial neural networks supporting Matlab and Py…☆327Updated 2 years ago
- PyTorch implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation☆334Updated 2 years ago
- Deep Anomaly Detection with Outlier Exposure (ICLR 2019)☆543Updated 2 years ago
- Open source release of the evaluation benchmark suite described in "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"☆458Updated 5 years ago
- Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).☆950Updated 6 months ago
- A repository for explaining feature attributions and feature interactions in deep neural networks.☆185Updated 2 years ago
- disentanglement_lib is an open-source library for research on learning disentangled representations.☆1,375Updated 3 years ago
- Model interpretability and understanding for PyTorch☆4,810Updated this week
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆415Updated 2 years ago
- This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpreta…☆337Updated 2 years ago
- PyTorch Library for Active Learning to accompany Human-in-the-Loop Machine Learning book☆930Updated last year