论文标题
通过解释揭开深层神经网络的神秘面纱：一项调查
Demystifying Deep Neural Networks Through Interpretation: A Survey
论文作者
论文摘要
现代的深度学习算法倾向于优化客观指标，例如最大程度地减少培训数据集中的跨熵损失，以便能够学习。问题在于，单个指标是对现实世界任务的不完整描述。单个指标无法解释为什么算法学习。当发生错误时，缺乏可解释性会导致理解和解决错误的硬性。最近，正在做一些工作来解决可解释性问题，以提供对神经网络行为和思维过程的见解。这些作品对于确定潜在的偏见和确保算法公平以及预期性能很重要。
Modern deep learning algorithms tend to optimize an objective metric, such as minimize a cross entropy loss on a training dataset, to be able to learn. The problem is that the single metric is an incomplete description of the real world tasks. The single metric cannot explain why the algorithm learn. When an erroneous happens, the lack of interpretability causes a hardness of understanding and fixing the error. Recently, there are works done to tackle the problem of interpretability to provide insights into neural networks behavior and thought process. The works are important to identify potential bias and to ensure algorithm fairness as well as expected performance.
