BriefGPT.xyz
Jun, 2021
走向完全可解释的深度神经网络：我们已经到达了吗？
Towards Fully Interpretable Deep Neural Networks: Are We There Yet?
HTML
PDF
Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee
TL;DR
本文提供了一个现有方法的回顾，以开发具有内在可解释性的DNN，重点关注卷积神经网络(CNNs)，旨在了解向完全可解释DNN的当前进展，并确定当前工作中的差距和潜在研究方向。
Abstract
Despite the remarkable performance,
deep neural networks
(DNNs) behave as
black-boxes
hindering user trust in Artificial Intelligence (AI) systems. Research on opening black-box DNN can be broadly categorized int
→