marcoancona / DeepExplain
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
☆746Updated 4 years ago
Alternatives and similar repositories for DeepExplain:
Users that are interested in DeepExplain are comparing it to the libraries listed below
- Public facing deeplift repo☆852Updated 2 years ago
- A toolbox to iNNvestigate neural networks' predictions!☆1,294Updated this week
- The LRP Toolbox provides simple and accessible stand-alone implementations of LRP for artificial neural networks supporting Matlab and Py…☆331Updated 2 years ago
- Attributing predictions made by the Inception network using the Integrated Gradients method☆617Updated 3 years ago
- Code for the TCAV ML interpretability project☆636Updated 8 months ago
- ☆913Updated 2 years ago
- Interesting resources related to XAI (Explainable Artificial Intelligence)☆825Updated 2 years ago
- Interpretability Methods for tf.keras models with Tensorflow 2.x☆1,025Updated 10 months ago
- Layer-wise Relevance Propagation (LRP) for LSTMs.☆225Updated 4 years ago
- Code for "High-Precision Model-Agnostic Explanations" paper☆801Updated 2 years ago
- Tensorflow tutorial for various Deep Neural Network visualization techniques☆347Updated 4 years ago
- ☆585Updated last year
- ☆264Updated 5 years ago
- Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers☆98Updated 6 years ago
- For calculating global feature importance using Shapley values.☆267Updated last week
- ☆100Updated 7 years ago
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)☆128Updated 3 years ago
- Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).☆973Updated last year
- Bayesian Deep Learning Benchmarks☆670Updated 2 years ago
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆222Updated 8 months ago
- Layers Outputs and Gradients in Keras. Made easy.☆1,058Updated last week
- All about explainable AI, algorithmic fairness and more☆107Updated last year
- Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations☆598Updated 2 months ago
- Code for all experiments.☆316Updated 4 years ago
- A repository for explaining feature attributions and feature interactions in deep neural networks.☆187Updated 3 years ago
- Python/Keras implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks" for explaining any model defin…☆217Updated 6 years ago
- Towards Automatic Concept-based Explanations☆159Updated 11 months ago
- Tuning hyperparams fast with Hyperband☆593Updated 6 years ago
- A PyTorch implementation of Neighbourhood Components Analysis.☆400Updated 4 years ago
- Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertaint…☆621Updated 2 years ago