hiranumn / IntegratedGradientsTF
Tensorflow implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks". It explains connections between two tensors.
☆16Updated 5 years ago
Related projects: ⓘ
- Keras implementation for DASP: Deep Approximate Shapley Propagation (ICML 2019)☆60Updated 5 years ago
- This repository is all about papers and tools of Explainable AI☆35Updated 4 years ago
- Papers on interpretable deep learning, for review☆27Updated 6 years ago
- Layerwise Relevance Propagation with Deep Taylor Series in TensorFlow☆71Updated 7 years ago
- ☆48Updated 4 years ago
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)☆124Updated 3 years ago
- Quantitative Testing with Concept Activation Vectors in PyTorch☆41Updated 5 years ago
- IBD: Interpretable Basis Decomposition for Visual Explanation☆51Updated 5 years ago
- DeViSE model (zero-shot learning) trained on ImageNet and deployed on AWS using Docker☆47Updated 5 years ago
- Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers☆96Updated 6 years ago
- ☆130Updated 5 years ago
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" ht…☆125Updated 3 years ago
- Code for Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks☆31Updated 6 years ago
- Model Patching: Closing the Subgroup Performance Gap with Data Augmentation☆42Updated 3 years ago
- How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods☆23Updated 3 years ago
- Codes for reproducing the contrastive explanation in “Explanations based on the Missing: Towards Contrastive Explanations with Pertinent…☆54Updated 6 years ago
- Interpretation of Neural Network is Fragile☆36Updated 4 months ago
- Tools for training explainable models using attribution priors.☆121Updated 3 years ago
- Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.☆126Updated 4 years ago
- Autoencoder network for imputing missing values☆26Updated 5 years ago
- Code for AAAI 2018 accepted paper: "Beyond Sparsity: Tree Regularization of Deep Models for Interpretability"☆77Updated 6 years ago
- Towards Automatic Concept-based Explanations☆154Updated 4 months ago
- Official repository for "Bridging Adversarial Robustness and Gradient Interpretability".☆29Updated 5 years ago
- Visualizing Deep Neural Network Decisions: Prediction Difference Analysis☆117Updated 6 years ago
- ☆99Updated 6 years ago
- Code/figures in Right for the Right Reasons☆54Updated 3 years ago
- Python implementation for evaluating explanations presented in "On the (In)fidelity and Sensitivity for Explanations" in NeurIPS 2019 for…☆24Updated 2 years ago
- TensorFlow implementation for SmoothGrad, Grad-CAM, Guided backprop, Integrated Gradients and other saliency techniques☆31Updated 3 years ago
- On disentangling the menagerie of disentanglement papers☆27Updated 4 years ago
- An uncertainty-based random sampling algorithm for data augmentation☆29Updated 4 years ago