88 results found Sort:

shap
shap shap
3.3k
23.1k
mit
245
A game theoretic approach to explain the output of any machine learning model.
shap shapley deep-learning explainability interpretability machine-learning gradient-boosting
Created 2016-11-22
2,780 commits to master branch, last one 7 days ago
EthicalML
awesome-production-machine-learning EthicalML
2.3k
17.7k
mit
407
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
mlops ml-ops awesome data-mining awesome-list deep-learning ml-operations production-ml explainability large-scale-ml responsible-ai interpretability machine-learning privacy-preserving privacy-preserving-ml machine-learning-operations production-machine-learning large-scale-machine-learning privacy-preserving-machine-learning
Created 2018-08-15
1,027 commits to master branch, last one 19 days ago
interpretml
interpret interpretml
736
6.3k
mit
146
Fit interpretable models. Explain blackbox machine learning.
ai iml xai bias blackbox interpretml scikit-learn transparency explainability explainable-ai explainable-ml interpretability interpretable-ai interpretable-ml machine-learning gradient-boosting differential-privacy artificial-intelligence interpretable-machine-learning
Created 2019-05-03
3,562 commits to develop branch, last one 2 days ago
MAIF
shapash MAIF
335
2.8k
apache-2.0
37
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
lime shap python transparency explainability explainable-ml interpretability machine-learning ethical-artificial-intelligence
Created 2020-04-29
1,700 commits to master branch, last one 11 days ago
hila-chefer
Transformer-Explainability hila-chefer
241
1.8k
mit
21
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
vit bert cvpr2021 bert-model perturbation deep-learning explainability attention-matrix vision-transformer attention-visualization visualize-classifications transformer-interpretability
Created 2020-11-23
86 commits to main branch, last one about a year ago
microsoft
responsible-ai-toolbox microsoft
375
1.4k
mit
33
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 libr...
ml ui widget jupyter widgets fairness fairness-ai fairness-ml data-science data-analysis visualization error-analysis explainability explainable-ai explainable-ml responsible-ai machinelearning interpretability machine-learning data-visualization
Created 2020-07-06
1,970 commits to main branch, last one 4 months ago
EthicalML
xai EthicalML
175
1.1k
mit
44
XAI - An eXplainability toolbox for machine learning
ai ml xai bias imbalance evaluation upsampling xai-library downsampling explainability explainable-ai explainable-ml bias-evaluation interpretability machine-learning feature-importance artificial-intelligence machine-learning-explainability
Created 2019-01-11
91 commits to master branch, last one 3 years ago
hila-chefer
Transformer-MM-Explainability hila-chefer
107
809
mit
8
[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-bas...
vqa clip detr lxmert visualbert transformer transformers visualization explainability explainable-ai interpretability
Created 2021-03-23
77 commits to main branch, last one about a year ago
h1st-ai
h1st h1st-ai
94
799
other
42
Power Tools for AI Engineers With Deadlines
automl avionics cold-start time-series data-science collaboration cybersecurity hacktoberfest explainability industrial-iot home-automation human-in-the-loop autonomous-vehicles energy-optimization predictive-maintenance datascience-environment trustworthy-datascience ensemble-machine-learning
Created 2020-08-13
817 commits to main branch, last one about a year ago
MisaOgura
flashtorch MisaOgura
87
737
mit
16
Visualization toolkit for neural networks in PyTorch! Demo -->
cnn pytorch deep-learning visualization explainability neural-networks interpretability machine-learning
Created 2019-03-22
127 commits to main branch, last one about a year ago
flyingdoog
awesome-graph-explainability-papers flyingdoog
68
671
unknown
28
Papers about explainability of GNNs
xai graph-mining deep-learning explainability explainable-ai machine-learning graph-neural-networks
Created 2021-11-01
282 commits to main branch, last one 23 days ago
alvinwan
neural-backed-decision-trees alvinwan
130
610
mit
18
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
cifar10 pytorch cifar100 imagenet tiny-imagenet decision-trees explainability neural-networks interpretability pretrained-models pretrained-weights image-classification neural-backed-decision-trees
Created 2020-03-20
830 commits to master branch, last one 3 years ago
explainX
explainx explainX
54
419
mit
10
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 @ ms...
xai bias blackbox explainx scikit-learn transparency aws-sagemaker explainability explainable-ai explainable-ml interpretability interpretable-ai machine-learning interpretable-machine-learning machine-learning-interpretability explainable-artificial-intelligence
Created 2020-06-16
192 commits to master branch, last one 4 months ago
haofanwang
Score-CAM haofanwang
66
408
mit
6
Official implementation of Score-CAM in PyTorch
cam gradcam heatmap pytorch grad-cam saliency scorecam score-cam gradient-free explainability cnn-visualization visual-explanations class-activation-maps cnn-visualization-technique
Created 2020-04-13
51 commits to master branch, last one 2 years ago
xmed-lab
CLIP_Surgery xmed-lab
26
376
unknown
5
CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks
sam clip multilabel multimodal segmentation explainability open-vocabulary interpretability segment-anything vision-transformer
Created 2023-04-11
9 commits to master branch, last one about a year ago
keisen
tf-keras-vis keisen
46
320
mit
8
Neural network visualization toolkit for tf.keras
xai keras python gradcam grad-cam saliency keras-vis score-cam tensorflow xai-library deep-learning saliency-maps visualization explainability explainable-ai explainable-ml gradcam-plus-plus keras-visualization activation-maximization
Created 2019-10-31
395 commits to master branch, last one 9 months ago
hbaniecki
adversarial-explainable-ai hbaniecki
45
302
cc-by-sa-4.0
15
💡 Adversarial attacks on explanations and how to defend them
iml xai deep model attacks defense security evaluation robustness adversarial interpretable counterfactual explainability explainable-ai responsible-ai interpretability adversarial-attacks adversarial-examples adversarial-machine-learning interpretable-machine-learning
Created 2020-07-30
124 commits to master branch, last one 21 days ago
carla-recourse
CARLA carla-recourse
62
283
mit
7
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
python pytorch recourse benchmark tensorflow tensorflow2 benchmarking counterfactual explainability explainable-ai explainable-ml counterfactuals machine-learning artificial-intelligence counterfactual-explanations
Created 2020-12-09
121 commits to main branch, last one about a year ago
mmschlk
shapiq mmschlk
13
265
mit
8
Shapley Interactions for Machine Learning
shap python shapiq shapley explainability interpretability machine-learning feature-interactions shapley-interactions
Created 2023-10-17
803 commits to main branch, last one a day ago
sebastian-hofstaetter
matchmaker sebastian-hofstaetter
30
261
apache-2.0
7
Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch
dpr pytorch neural-ir efficiency transformer explainability neural-ranking knowledge-distillation
Created 2019-10-30
12 commits to master branch, last one 3 years ago
iancovert
sage iancovert
34
257
mit
6
For calculating global feature importance using Shapley values.
shapley explainability interpretability machine-learning
Created 2020-03-13
97 commits to master branch, last one 3 days ago
dmlc
GNNLens2 dmlc
27
242
apache-2.0
11
Visualization tool for Graph Neural Networks
dgl xai pytorch deep-learning visualization explainability graph-visualization graph-neural-networks graph-representation-learning
Created 2021-08-30
36 commits to main branch, last one 2 years ago
AI4LIFE-GROUP
OpenXAI AI4LIFE-GROUP
40
235
mit
8
OpenXAI : Towards a Transparent Evaluation of Model Explanations
benchmark leaderboard explainability explainable-ai reproducibility interpretability
Created 2022-06-08
179 commits to main branch, last one 8 months ago
chr5tphr
zennit chr5tphr
32
205
other
15
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
lrp xai python pytorch attribution deep-learning explainability explainable-ai interpretability interpretable-ai interpretable-ml machine-learning feature-attribution
Created 2020-11-10
232 commits to master branch, last one 8 months ago
hate-alert
HateXplain hate-alert
64
191
mit
7
Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.
bias lstm detection offensive bert-model hatespeech hate-speech attention-lstm explainability bert-fine-tuning interpretable-deep-learning
Created 2020-05-01
92 commits to master branch, last one 2 years ago
squaredev-io
whitebox squaredev-io
5
183
mit
6
[Not Actively Maintained] Whitebox is an open source E2E ML monitoring platform with edge capabilities that plays nicely with kubernetes
k8s xai mlops mlflow python recall accuracy f1-score modelops kubernetes monitoring ml-monitoring observability accuracy-score explainability explainable-ai accuracy-metrics confusion-matrix machine-learning model-monitoring
Created 2022-09-09
151 commits to main branch, last one about a year ago
all-things-vits
code-samples all-things-vits
10
177
apache-2.0
6
Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.
timm cvpr2023 tutorial attention diffusers transformers explainability vision-transformers representation-learning
Created 2023-06-08
25 commits to main branch, last one about a year ago
mims-harvard
GraphXAI mims-harvard
29
177
mit
6
GraphXAI: Resource to support the development and evaluation of GNN explainers
embeddings benchmarking deep-learning explainability explainable-ai explainable-ml interpretability graph-neural-networks graph-machine-learning
Created 2021-06-16
736 commits to main branch, last one about a year ago
csinva
imodelsX csinva
25
162
mit
6
Scikit-learn friendly library to interpret, and prompt-engineer text datasets using large language models.
ai ml xai text pytorch huggingface scikit-learn deep-learning explainability language-model neural-network interpretability machine-learning transformer-models text-classification natural-language-processing natural-language-understanding
Created 2022-10-04
346 commits to master branch, last one about a month ago
feedzai
timeshap feedzai
30
162
other
14
TimeSHAP explains Recurrent Neural Network predictions.
rnn shap explainability shapley-values
Created 2022-01-10
53 commits to main branch, last one about a year ago