EDiT

Model interpreter

An implementation of a method to interpret ensemble models by learning compact representations from them

EDiT: Interpreting Ensemble Models via Compact Soft Decision Trees (ICDM'19)

GitHub

8 stars
2 watching
4 forks
Language: Python
last commit: about 7 years ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
jianbo-lab/l2xA Python framework for learning to interpret models using information-theoretic methods123
applieddatasciencepartners/xgboostexplainerProvides tools to understand and interpret the decisions made by XGBoost models in machine learning253
h2oai/mli-resourcesProvides tools and techniques for interpreting machine learning models483
interpretml/diceProvides counterfactual explanations for machine learning models to facilitate interpretability and understanding.1,373
declare-lab/instruct-evalAn evaluation framework for large language models trained with instruction tuning methods535
mayer79/flashlightA toolset for understanding and interpreting complex machine learning models22
csinva/imodelsAn open-source package that provides interpretable machine learning models compatible with scikit-learn.1,406
openai/simple-evalsEvaluates language models using standardized benchmarks and prompting techniques.2,059
allenai/olmo-evalA framework for evaluating language models on NLP tasks326
phipsgabler/operajonalA JavaScript implementation of an operational monad style for recursive program interpretation6
ukplab/linspectorA framework to interpret multilingual NLP models and understand their word representations.24
datamllab/xdeepProvides tools for interpreting deep neural networks42
quchen/stgiAn interpreter for a visual programming model to help understand Haskell's execution model529
maluuba/nlg-evalA toolset for evaluating and comparing natural language generation models1,350
cofinalsubnets/wispA Haskell-based interpreted Lisp language with features like lexical closures and continuations, designed to be easily embedded in other programs.115