论文标题
中途认识您：解释深度学习的奥秘
Meet You Halfway: Explaining Deep Learning Mysteries
论文作者
论文摘要
深度神经网络在具有最新结果的各种学习任务上表现出色。尽管这些模型具有很高的表现力，并且具有出色的概括能力，但它们容易受到较小的扰动的影响。遭受这种扰动的样本称为“对抗性例子”。即使深度学习是一个广泛研究的领域，但有关深度学习模型本质的许多问题仍未得到答复。在本文中，我们介绍了一个新的概念框架，该概念框架附带了正式描述，旨在阐明网络的行为并解释学习过程的幕后花絮。我们的框架为有关深度学习的固有问题提供了解释。特别是我们澄清：（1）为什么神经网络能获得概括能力？ （2）为什么对抗示例在不同模型之间转移？我们提供了一组全面的实验，以支持这一新框架及其基本理论。
Deep neural networks perform exceptionally well on various learning tasks with state-of-the-art results. While these models are highly expressive and achieve impressively accurate solutions with excellent generalization abilities, they are susceptible to minor perturbations. Samples that suffer such perturbations are known as "adversarial examples". Even though deep learning is an extensively researched field, many questions about the nature of deep learning models remain unanswered. In this paper, we introduce a new conceptual framework attached with a formal description that aims to shed light on the network's behavior and interpret the behind-the-scenes of the learning process. Our framework provides an explanation for inherent questions concerning deep learning. Particularly, we clarify: (1) Why do neural networks acquire generalization abilities? (2) Why do adversarial examples transfer between different models?. We provide a comprehensive set of experiments that support this new framework, as well as its underlying theory.
