A toolbox to iNNvestigate neural networks' predictions!
Project Page // Paper // No-code Web Demo // Colab Notebook
This repository contains a sample implementation of Gradient Feature Auditing (GFA) meant to be generalizable to most datasets. For more information on the repair process, see our paper on Certifying and Removing Disparate Impact. For information on the full auditing process, see our paper on…
Principalele funcționalități ale algofairness/blackboxauditing sunt: Explainable AI Libraries.
Alternativele open-source pentru algofairness/blackboxauditing includ: albermax/innvestigate — A toolbox to iNNvestigate neural networks' predictions! alvinwan/neural-backed-decision-trees — Project Page // Paper // No-code Web Demo // Colab Notebook. andosa/treeinterpreter — TreeInterpreter. ankurtaly/integrated-gradients — (a.k.a. Path-Integrated Gradients, a.k.a. Axiomatic Attribution for Deep Networks). austinrochford/pycebox — ⬛ Python Individual Conditional Expectation Plot Toolbox. aerdem4/lofo-importance — Leave One Feature Out Importance.