Metadata-Version: 2.1
Name: fcp-xai
Version: 0.1.1
Summary: Forward Composition Propagation
Home-page: https://github.com/igraugar/fcp
Author: Isel Grau, Gonzalo Nápoles
Author-email: i.d.c.grau.garcia@tue.nl, g.r.napoles@uvt.nl
License: Apache License 2.0
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: MacOS
Classifier: Programming Language :: Python :: 3.8
License-File: LICENSE

Forward Composition Propagation (FCP) is a post-hoc XAI method for explaining the predictions of feed-forward neural networks trained on structured classification problems. Each neuron is described by a composition vector indicating the role of each problem feature in that neuron.
