explainability

There are 17 repositories under explainability topic.

shap / shap
A game theoretic approach to explain the output of any machine learning model.
interpretability machine-learning deep-learning gradient-boosting shap shapley explainability
Language:Jupyter Notebook 21578
EthicalML / awesome-production-machine-learning
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
machine-learning mlops interpretability explainability responsible-ai deep-learning machine-learning-operations ml-ops ml-operations privacy-preserving privacy-preserving-ml privacy-preserving-machine-learning data-mining large-scale-ml production-ml large-scale-machine-learning production-machine-learning awesome awesome-list
15924
interpretml / interpret
Fit interpretable models. Explain blackbox machine learning.
machine-learning interpretability gradient-boosting blackbox scikit-learn xai interpretml interpretable-machine-learning interpretable-ai transparency iml interpretable-ml explainable-ml explainability bias ai artificial-intelligence explainable-ai differential-privacy
Language:C++ 5988
MAIF / shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
python machine-learning explainability explainable-ml transparency ethical-artificial-intelligence shap lime interpretability
Language:Jupyter Notebook 2640
hila-chefer / Transformer-Explainability
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
deep-learning vision-transformer bert-model bert explainability transformer-interpretability perturbation attention-visualization visualize-classifications vit attention-matrix cvpr2021
Language:Jupyter Notebook 1659
microsoft / responsible-ai-toolbox
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.
ui responsible-ai data-science fairness fairness-ml fairness-ai explainable-ai explainable-ml explainability machinelearning machine-learning ml visualization widgets widget jupyter error-analysis data-analysis data-visualization interpretability
Language:TypeScript 1205
EthicalML / xai
XAI - An eXplainability toolbox for machine learning
explainability xai ml ai bias artificial-intelligence bias-evaluation explainable-ai explainable-ml machine-learning machine-learning-explainability interpretability xai-library evaluation imbalance upsampling downsampling feature-importance
Language:Python 1057
h1st-ai / h1st
Power Tools for AI Engineers With Deadlines
data-science explainability home-automation time-series collaboration cybersecurity cold-start autonomous-vehicles automl avionics human-in-the-loop predictive-maintenance ensemble-machine-learning datascience-environment industrial-iot trustworthy-datascience energy-optimization hacktoberfest
Language:Jupyter Notebook 791
MisaOgura / flashtorch
Visualization toolkit for neural networks in PyTorch! Demo -->
cnn deep-learning explainability interpretability machine-learning neural-networks pytorch visualization
Language:HTML 722
hila-chefer / 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.
transformers transformer vqa detr visualization explainability explainable-ai interpretability lxmert visualbert clip
Language:Jupyter Notebook 701
alvinwan / neural-backed-decision-trees
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
decision-trees neural-networks image-classification explainability tiny-imagenet cifar10 cifar100 interpretability imagenet neural-backed-decision-trees pretrained-weights pretrained-models pytorch
Language:Python 599
flyingdoog / awesome-graph-explainability-papers
Papers about explainability of GNNs
machine-learning deep-learning graph-mining graph-neural-networks xai explainable-ai explainability
542
explainx
explainX / explainx
Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code. We are looking for co-authors to take this project forward. Reach out @ ms8909@nyu.edu
explainable-ai explainable-artificial-intelligence machine-learning interpretability blackbox xai explainx interpretable-ai transparency bias interpretable-machine-learning aws-sagemaker explainability explainable-ml machine-learning-interpretability scikit-learn
Language:Jupyter Notebook 388
haofanwang / Score-CAM
Official implementation of Score-CAM in PyTorch
score-cam cam cnn-visualization-technique saliency cnn-visualization pytorch visual-explanations explainability class-activation-maps gradient-free heatmap scorecam grad-cam gradcam
Language:Python 382
keisen / tf-keras-vis
Neural network visualization toolkit for tf.keras
activation-maximization saliency-maps visualization keras keras-visualization saliency tensorflow gradcam-plus-plus score-cam grad-cam keras-vis gradcam explainability explainable-ai explainable-ml deep-learning python xai xai-library
Language:Python 304
xmed-lab / CLIP_Surgery
CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks
clip sam explainability multimodal multilabel segmentation open-vocabulary segment-anything interpretability vision-transformer
Language:Jupyter Notebook 285
adversarial-explainable-ai
hbaniecki / adversarial-explainable-ai
💡 Adversarial attacks on explanations and how to defend them
interpretable-machine-learning adversarial-machine-learning iml adversarial-attacks interpretability xai explainable-ai adversarial-examples explainability attacks security responsible-ai robustness interpretable adversarial model evaluation deep counterfactual defense
278
carla-recourse / CARLA
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
python machine-learning artificial-intelligence explainable-ai explainable-ml explainability counterfactual-explanations counterfactuals counterfactual recourse benchmark benchmarking tensorflow tensorflow2 pytorch
Language:Python 263
sebastian-hofstaetter / matchmaker
Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch
neural-ir transformer explainability efficiency knowledge-distillation dpr pytorch neural-ranking
Language:Python 254
iancovert / sage
For calculating global feature importance using Shapley values.
explainability interpretability shapley machine-learning
Language:Python 231
AI4LIFE-GROUP / OpenXAI
OpenXAI : Towards a Transparent Evaluation of Model Explanations
benchmark explainability explainable-ai interpretability leaderboard reproducibility
Language:JavaScript 213
dmlc / GNNLens2
Visualization tool for Graph Neural Networks
graph-neural-networks explainability deep-learning dgl graph-representation-learning visualization graph-visualization pytorch xai
Language:TypeScript 207
whitebox
squaredev-io / whitebox
[Not Actively Maintained] Whitebox is an open source E2E ML monitoring platform with edge capabilities that plays nicely with kubernetes
machine-learning monitoring observability python explainability explainable-ai ml-monitoring mlflow mlops modelops accuracy accuracy-metrics accuracy-score confusion-matrix f1-score recall model-monitoring k8s kubernetes xai
Language:Python 181
chr5tphr / zennit
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
lrp pytorch xai machine-learning attribution explainability python interpretability explainable-ai interpretable-ai feature-attribution interpretable-ml deep-learning
Language:Python 174
hate-alert / HateXplain
Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.
explainability hate-speech bias offensive detection hatespeech interpretable-deep-learning bert-model lstm attention-lstm bert-fine-tuning
Language:Python 174
all-things-vits / code-samples
Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.
attention cvpr2023 diffusers explainability representation-learning timm transformers tutorial vision-transformers
Language:Jupyter Notebook 151
marakeby / pnet_prostate_paper
P-NET, Biologically informed deep neural network for prostate cancer classification and discovery
sparse explainability cancer
Language:HTML 145
feedzai / timeshap
TimeSHAP explains Recurrent Neural Network predictions.
explainability rnn shap shapley-values
Language:Jupyter Notebook 142
DFKI-NLP / thermostat
Collection of NLP model explanations and accompanying analysis tools
explainability interpretability natural-language-processing transformers datasets feature-attribution saliency-maps heatmaps captum explainable-nlp
Language:Jsonnet 141
mims-harvard / GraphXAI
GraphXAI: Resource to support the development and evaluation of GNN explainers
graph-neural-networks explainability explainable-ai explainable-ml interpretability deep-learning embeddings graph-machine-learning benchmarking
Language:Python 135
pkuserc / ChatGPT_for_IE
Evaluating ChatGPT’s Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness
calibration chatgpt entity-typing evaluation event-detection event-extraction explainability information-extraction named-entity-recognition performance relation-classification relation-extraction faithfulness large-language-models
Language:Python 133
awesome-shapley-value
AstraZeneca / awesome-shapley-value
Reading list for "The Shapley Value in Machine Learning" (JCAI 2022)
artificial-intelligence deep-learning machine-learning shapley shapley-additive-explanations shapley-value xai data-science explainability explainable lime shap explainable-ai explainable-artificial-intelligence explainable-ml shapley-decomposition shapley-q-value owen-value
131
pietrobarbiero / pytorch_explain
PyTorch Explain: Interpretable Deep Learning in Python.
logic pytorch python machine-learning neural-network deep-learning explainability explainable-ai lens entropy sympy interpretability interpretable-ai interpretable-deep-learning interpretable-machine-learning
Language:Jupyter Notebook 127
d909b / cxplain
Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.
deep-learning explainability explainable-ai explainable-ml interpretability machine-learning
Language:Python 123
deep-explanation-penalization
laura-rieger / deep-explanation-penalization
Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584
interpretability neural-network machine-learning convolutional-neural-network pytorch explainability deep-learning explainable-ai artificial-intelligence ml ai python data-science jupyter-notebook feature-importance recurrent-neural-network fairness fairness-ml cdep interpretable-deep-learning
Language:Jupyter Notebook 123
hierarchical-dnn-interpretations
csinva / hierarchical-dnn-interpretations
Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)
interpretability neural-network machine-learning convolutional-neural-networks pytorch interpretation explainability deep-learning explainable-ai artificial-intelligence ml ai python data-science jupyter-notebook deep-neural-networks acd statistics feature-importance iclr
Language:Jupyter Notebook 122