Transformer-MM-Explainability[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.
Stars: ✭ 484 (+3357.14%)
deep-explanation-penalizationCode for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584
Stars: ✭ 110 (+685.71%)
mllpThe code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".
Stars: ✭ 15 (+7.14%)
transformers-interpretModel explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.
Stars: ✭ 861 (+6050%)
CARLACARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
Stars: ✭ 166 (+1085.71%)
zennitZennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
Stars: ✭ 57 (+307.14%)
PyDGNA research library for Deep Graph Networks
Stars: ✭ 158 (+1028.57%)
ProtoTreeProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
Stars: ✭ 47 (+235.71%)
hierarchical-dnn-interpretationsUsing / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)
Stars: ✭ 110 (+685.71%)
InterpretFit interpretable models. Explain blackbox machine learning.
Stars: ✭ 4,352 (+30985.71%)
concept-based-xaiLibrary implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
Stars: ✭ 41 (+192.86%)
adaptive-waveletsAdaptive, interpretable wavelets across domains (NeurIPS 2021)
Stars: ✭ 58 (+314.29%)
Modelstudio📍 Interactive Studio for Explanatory Model Analysis
Stars: ✭ 163 (+1064.29%)
StellargraphStellarGraph - Machine Learning on Graphs
Stars: ✭ 2,235 (+15864.29%)
Visual AttributionPytorch Implementation of recent visual attribution methods for model interpretability
Stars: ✭ 127 (+807.14%)
XAIatERUM2020Workshop: Explanation and exploration of machine learning models with R and DALEX at eRum 2020
Stars: ✭ 52 (+271.43%)
BreakdownModel Agnostics breakDown plots
Stars: ✭ 93 (+564.29%)
Interpretability By PartsCode repository for "Interpretable and Accurate Fine-grained Recognition via Region Grouping", CVPR 2020 (Oral)
Stars: ✭ 88 (+528.57%)
pyCeterisParibusPython library for Ceteris Paribus Plots (What-if plots)
Stars: ✭ 19 (+35.71%)
ArenaRData generator for Arena - interactive XAI dashboard
Stars: ✭ 28 (+100%)
expmrcExpMRC: Explainability Evaluation for Machine Reading Comprehension
Stars: ✭ 58 (+314.29%)
self critical vqaCode for NeurIPS 2019 paper ``Self-Critical Reasoning for Robust Visual Question Answering''
Stars: ✭ 39 (+178.57%)
ShapA game theoretic approach to explain the output of any machine learning model.
Stars: ✭ 14,917 (+106450%)
kernel-modNeurIPS 2018. Linear-time model comparison tests.
Stars: ✭ 17 (+21.43%)
Lrp for lstmLayer-wise Relevance Propagation (LRP) for LSTMs
Stars: ✭ 152 (+985.71%)
bert attn vizVisualize BERT's self-attention layers on text classification tasks
Stars: ✭ 41 (+192.86%)
thermostatCollection of NLP model explanations and accompanying analysis tools
Stars: ✭ 126 (+800%)
Pycebox⬛ Python Individual Conditional Expectation Plot Toolbox
Stars: ✭ 101 (+621.43%)
adversarial-robustness-publicCode for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"
Stars: ✭ 49 (+250%)
datafsmMachine Learning Finite State Machine Models from Data with Genetic Algorithms
Stars: ✭ 14 (+0%)
CxplainCausal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.
Stars: ✭ 84 (+500%)
xai-iml-sotaInteresting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.
Stars: ✭ 51 (+264.29%)
Cnn Interpretability🏥 Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease
Stars: ✭ 68 (+385.71%)
mindsdb serverMindsDB server allows you to consume and expose MindsDB workflows, through http.
Stars: ✭ 3 (-78.57%)
AthenaAutomatic equation building and curve fitting. Runs on Tensorflow. Built for academia and research.
Stars: ✭ 57 (+307.14%)
dlime experimentsIn this work, we propose a deterministic version of Local Interpretable Model Agnostic Explanations (LIME) and the experimental results on three different medical datasets shows the superiority for Deterministic Local Interpretable Model-Agnostic Explanations (DLIME).
Stars: ✭ 21 (+50%)
Torch CamClass activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM)
Stars: ✭ 249 (+1678.57%)
Text nnText classification models. Used a submodule for other projects.
Stars: ✭ 55 (+292.86%)
TrelawneyGeneral Interpretability Package
Stars: ✭ 55 (+292.86%)
ContrastiveexplanationContrastive Explanation (Foil Trees), developed at TNO/Utrecht University
Stars: ✭ 36 (+157.14%)
ALPS 2021XAI Tutorial for the Explainable AI track in the ALPS winter school 2021
Stars: ✭ 55 (+292.86%)
Symbolic MetamodelingCodebase for "Demystifying Black-box Models with Symbolic Metamodels", NeurIPS 2019.
Stars: ✭ 29 (+107.14%)
AlibiAlgorithms for monitoring and explaining machine learning models
Stars: ✭ 924 (+6500%)
CaptumModel interpretability and understanding for PyTorch
Stars: ✭ 2,830 (+20114.29%)
Grad Cam[ICCV 2017] Torch code for Grad-CAM
Stars: ✭ 891 (+6264.29%)
DalexmoDel Agnostic Language for Exploration and eXplanation
Stars: ✭ 795 (+5578.57%)
EgoCNNCode for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures" (ICML 2019)
Stars: ✭ 16 (+14.29%)
3D-GuidedGradCAM-for-Medical-ImagingThis Repo containes the implemnetation of generating Guided-GradCAM for 3D medical Imaging using Nifti file in tensorflow 2.0. Different input files can be used in that case need to edit the input to the Guided-gradCAM model.
Stars: ✭ 60 (+328.57%)
ExplainxExplainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code.
Stars: ✭ 196 (+1300%)
Tf ExplainInterpretability Methods for tf.keras models with Tensorflow 2.x
Stars: ✭ 780 (+5471.43%)
Ad examplesA collection of anomaly detection methods (iid/point-based, graph and time series) including active learning for anomaly detection/discovery, bayesian rule-mining, description for diversity/explanation/interpretability. Analysis of incorporating label feedback with ensemble and tree-based detectors. Includes adversarial attacks with Graph Convolutional Network.
Stars: ✭ 641 (+4478.57%)