zennitZennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
Stars: ✭ 57 (-1.72%)
concept-based-xaiLibrary implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
Stars: ✭ 41 (-29.31%)
InterpretFit interpretable models. Explain blackbox machine learning.
Stars: ✭ 4,352 (+7403.45%)
mllpThe code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".
Stars: ✭ 15 (-74.14%)
ArenaRData generator for Arena - interactive XAI dashboard
Stars: ✭ 28 (-51.72%)
removal-explanationsA lightweight implementation of removal-based explanations for ML models.
Stars: ✭ 46 (-20.69%)
interpretable-mlTechniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.
Stars: ✭ 17 (-70.69%)
ALPS 2021XAI Tutorial for the Explainable AI track in the ALPS winter school 2021
Stars: ✭ 55 (-5.17%)
ProtoTreeProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
Stars: ✭ 47 (-18.97%)
hierarchical-dnn-interpretationsUsing / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)
Stars: ✭ 110 (+89.66%)
diabetes use caseSample use case for Xavier AI in Healthcare conference: https://www.xavierhealth.org/ai-summit-day2/
Stars: ✭ 22 (-62.07%)
GNNLens2Visualization tool for Graph Neural Networks
Stars: ✭ 155 (+167.24%)
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 (+89.66%)
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 (+734.48%)
ShapA game theoretic approach to explain the output of any machine learning model.
Stars: ✭ 14,917 (+25618.97%)
xai-iml-sotaInteresting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.
Stars: ✭ 51 (-12.07%)
sageFor calculating global feature importance using Shapley values.
Stars: ✭ 129 (+122.41%)
thermostatCollection of NLP model explanations and accompanying analysis tools
Stars: ✭ 126 (+117.24%)
Symbolic MetamodelingCodebase for "Demystifying Black-box Models with Symbolic Metamodels", NeurIPS 2019.
Stars: ✭ 29 (-50%)
StellargraphStellarGraph - Machine Learning on Graphs
Stars: ✭ 2,235 (+3753.45%)
Grad Cam[ICCV 2017] Torch code for Grad-CAM
Stars: ✭ 891 (+1436.21%)
Tf ExplainInterpretability Methods for tf.keras models with Tensorflow 2.x
Stars: ✭ 780 (+1244.83%)
ExplainxExplainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code.
Stars: ✭ 196 (+237.93%)
Visual AttributionPytorch Implementation of recent visual attribution methods for model interpretability
Stars: ✭ 127 (+118.97%)
ContrastiveexplanationContrastive Explanation (Foil Trees), developed at TNO/Utrecht University
Stars: ✭ 36 (-37.93%)
Lrp for lstmLayer-wise Relevance Propagation (LRP) for LSTMs
Stars: ✭ 152 (+162.07%)
AlibiAlgorithms for monitoring and explaining machine learning models
Stars: ✭ 924 (+1493.1%)
CaptumModel interpretability and understanding for PyTorch
Stars: ✭ 2,830 (+4779.31%)
DalexmoDel Agnostic Language for Exploration and eXplanation
Stars: ✭ 795 (+1270.69%)
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 (+1005.17%)
mindsdb nativeMachine Learning in one line of code
Stars: ✭ 34 (-41.38%)
XaiXAI - An eXplainability toolbox for machine learning
Stars: ✭ 596 (+927.59%)
Pycebox⬛ Python Individual Conditional Expectation Plot Toolbox
Stars: ✭ 101 (+74.14%)
FlashtorchVisualization toolkit for neural networks in PyTorch! Demo -->
Stars: ✭ 561 (+867.24%)
Xai resourcesInteresting resources related to XAI (Explainable Artificial Intelligence)
Stars: ✭ 553 (+853.45%)
BreakdownModel Agnostics breakDown plots
Stars: ✭ 93 (+60.34%)
Interpretable machine learning with pythonExamples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.
Stars: ✭ 530 (+813.79%)
DeepliftPublic facing deeplift repo
Stars: ✭ 512 (+782.76%)
TcavCode for the TCAV ML interpretability project
Stars: ✭ 442 (+662.07%)
LucidA collection of infrastructure and tools for research in neural network interpretability.
Stars: ✭ 4,344 (+7389.66%)
ZAQ-codeCVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)
Stars: ✭ 59 (+1.72%)
mindsdb serverMindsDB server allows you to consume and expose MindsDB workflows, through http.
Stars: ✭ 3 (-94.83%)
ImodelsInterpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
Stars: ✭ 194 (+234.48%)
Interpretability By PartsCode repository for "Interpretable and Accurate Fine-grained Recognition via Region Grouping", CVPR 2020 (Oral)
Stars: ✭ 88 (+51.72%)
Mli ResourcesH2O.ai Machine Learning Interpretability Resources
Stars: ✭ 428 (+637.93%)
Neural Backed Decision TreesMaking decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
Stars: ✭ 411 (+608.62%)
CxplainCausal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.
Stars: ✭ 84 (+44.83%)
Pyss3A Python package implementing a new machine learning model for text classification with visualization tools for Explainable AI
Stars: ✭ 191 (+229.31%)
FacetHuman-explainable AI.
Stars: ✭ 269 (+363.79%)
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 (+329.31%)
Cnn Interpretability🏥 Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease
Stars: ✭ 68 (+17.24%)