Hide-and-Seek: A Template for Explainable AI

Autor:	Tagaris, Thanos, Stafylopatis, Andreas
Rok vydání:	2020
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Statistics - Machine Learning 62M45 I.2.6
Druh dokumentu:	Working Paper
Popis:	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. Comment: 24 pages, 14 figures. Submitted on a special issue for Explainable AI, on Elsevier's "Artificial Intelligence"
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2005.00130 Zobrazit plný text záznamu View this record from Arxiv