anchor
Explainers
Provides a method to generate explanations for predictions made by any black box classifier.
Code for "High-Precision Model-Agnostic Explanations" paper
798 stars
28 watching
114 forks
Language: Jupyter Notebook
last commit: over 2 years ago
Linked from 3 awesome lists
ethicalml/awesome-production-machine-learning
jphall663/awesome-machine-learning-interpretability
krzjoa/awesome-python-data-scienceRelated projects:
| Repository | Description | Stars |
|---|---|---|
 thomasp85/lime | An R package for providing explanations of predictions made by black box classifiers. | 485 |
 rmarko/explainprediction | An R package for explaining the predictions made by machine learning models in data science applications. | 2 |
 modeloriented/modelstudio | A tool for creating interactive, model-agnostic explanations of machine learning models in R | 326 |
| modeloriented/dalex | A tool to help understand and explain the behavior of complex machine learning models | 1,375 |
 pbiecek/xaiaterum2020 | An R package and workshop materials for explaining machine learning models using explainable AI techniques | 52 |
 giuseppec/iml | Provides methods to interpret and explain the behavior of machine learning models | 492 |
| modeloriented/ibreakdown | A tool for explaining predictions from machine learning models by attributing them to specific input variables and their interactions. | 81 |
 neso613/asr_tflite | Provides pre-trained ASR models for efficient inference using TFLite | 11 |
 apple/ml-no-token-left-behind | A PyTorch implementation of an explainability-aided image classification and generation system | 138 |
 explainx/explainx | Provides a framework to understand and explain the behavior of machine learning models used in data science applications. | 417 |
 jalammar/ecco | An interactive visualization library for exploring and understanding transformer-based language models | 1,985 |
 marcelrobeer/contrastiveexplanation | Provides explanations for why an instance has a certain outcome by contrasting it with what would have happened if the outcome had been different. | 45 |
 interpretml/dice | Provides counterfactual explanations for machine learning models to facilitate interpretability and understanding. | 1,364 |
 jbloomaus/decisiontransformerinterpretability | An open-source project that provides tools and utilities to understand how transformers are used in reinforcement learning tasks. | 73 |
 hughjdavey/aoc-kotlin-starter | A starter template for solving Advent of Code puzzles in Kotlin | 22 |