论文标题
捉迷藏：可解释AI的模板
Hide-and-Seek: A Template for Explainable AI
论文作者
论文摘要
缺乏透明度的是神经网络及其在行业中的广泛采用。尽管有很大的兴趣，但这种缺点尚未得到充分解决。这项研究提出了一个名为“捉迷藏”（HNS）的新型框架，用于培训可解释的神经网络，并为探索和比较类似思想建立了理论基础。广泛的实验表明，可以将高度的可解释性归因于神经网络，而无需牺牲其预测能力。
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.
