Lack of transparency has been the Achilles heal of Neural Networks and their wider adoption in industry. Despite significant interest this shortcoming has not been adequately addressed. This study proposes a novel framework called Hide-and-Seek (HnS) for training Interpretable Neural Networks and establishes a theoretical foundation for exploring and comparing similar ideas. Extensive experimentation indicates that a high degree of interpretability can be imputed into Neural Networks, without sacrificing their predictive power.
@article{arxiv.2005.00130,
title = {Hide-and-Seek: A Template for Explainable AI},
author = {Thanos Tagaris and Andreas Stafylopatis},
journal= {arXiv preprint arXiv:2005.00130},
year = {2020}
}
Comments
24 pages, 14 figures. Submitted on a special issue for Explainable AI, on Elsevier's "Artificial Intelligence"