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 5 years ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

Repository Description Stars
jianbo-lab/l2x A Python framework for learning to interpret models using information-theoretic methods 124
applieddatasciencepartners/xgboostexplainer Provides tools to understand and interpret the decisions made by XGBoost models in machine learning 252
h2oai/mli-resources Provides tools and techniques for interpreting machine learning models 484
interpretml/dice Provides counterfactual explanations for machine learning models to facilitate interpretability and understanding. 1,364
declare-lab/instruct-eval An evaluation framework for large language models trained with instruction tuning methods 528
mayer79/flashlight A toolset for understanding and interpreting complex machine learning models 22
csinva/imodels An open-source package that provides interpretable machine learning models compatible with scikit-learn. 1,399
openai/simple-evals A library for evaluating language models using standardized prompts and benchmarking tests. 1,939
allenai/olmo-eval An evaluation framework for large language models. 310
phipsgabler/operajonal A JavaScript implementation of an operational monad style for recursive program interpretation 6
ukplab/linspector A framework to interpret multilingual NLP models and understand their word representations. 23
datamllab/xdeep Provides tools for interpreting deep neural networks 42
quchen/stgi An interpreter for a visual programming model to help understand Haskell's execution model 527
maluuba/nlg-eval A toolset for evaluating and comparing natural language generation models 1,347
cofinalsubnets/wisp A Haskell-based interpreted Lisp language with features like lexical closures and continuations, designed to be easily embedded in other programs. 115