arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.11917cs.LGcs.AI
收藏

对抗性示例和更深层次的归纳之谜:深度学习中对伪影理论的需求

Adversarial Examples and the Deeper Riddle of Induction: The Need for a Theory of Artifacts in Deep Learning

The University of Houston(休斯顿大学)

Cameron Buckner

摘要:

深度学习是目前人工智能中应用最广泛、最成功的技术。它有望推动科学发现的前沿超越目前的限制。然而,怀疑论者担心深层神经网络是黑匣子,并质疑如果人类无法理解它们,这些进步是否真的可以被视为科学进步。与此相关的是,这些系统还具有令人困惑的新漏洞:最明显的是对“对抗性示例”的敏感性。在本文中,我认为,对抗性的例子将成为哲学和各种科学辩论的热点。具体而言,关于对抗性示例的新发现挑战了共识观点,即网络对这些情况的判决是由训练集中的过度拟合特质噪声引起的,并且可能是检测人类无法感知的预测有用的“数据几何结构的内在特征”的结果(Ilyas et al.,2019年)。这些结果应该促使我们重新审视对哲学和科学交叉点上最深刻的谜题之一的回应:纳尔逊·古德曼的归纳法“新之谜”。具体来说,它们提出了一种可能性,即许多科学的进步将取决于对人类难以理解的有用特征的检测和操纵。然而,在我们评估这种可能性之前,我们必须确定哪些(如果有的话)这些难以理解的特征是真实的,但只适用于“外星人”的感知和认知,哪些是深度学习的独特伪像--因为像镜头耀斑或吉布斯现象这样的伪像对预测同样有用,但通常被视为科学理论化的障碍。因此,机器学习研究人员迫切需要为深度神经网络开发一种伪影理论,最后,我为这一研究领域勾画了一些初步方向。

英文摘要:

Deep learning is currently the most widespread and successful technology in artificial intelligence. It promises to push the frontier of scientific discovery beyond current limits. However, skeptics have worried that deep neural networks are black boxes, and have called into question whether these advances can really be deemed scientific progress if humans cannot understand them. Relatedly, these systems also possess bewildering new vulnerabilities: most notably a susceptibility to "adversarial examples". In this paper, I argue that adversarial examples will become a flashpoint of debate in philosophy and diverse sciences. Specifically, new findings concerning adversarial examples have challenged the consensus view that the networks' verdicts on these cases are caused by overfitting idiosyncratic noise in the training set, and may instead be the result of detecting predictively useful "intrinsic features of the data geometry" that humans cannot perceive (Ilyas et al., 2019). These results should cause us to re-examine responses to one of the deepest puzzles at the intersection of philosophy and science: Nelson Goodman's "new riddle" of induction. Specifically, they raise the possibility that progress in a number of sciences will depend upon the detection and manipulation of useful features that humans find inscrutable. Before we can evaluate this possibility, however, we must decide which (if any) of these inscrutable features are real but available only to "alien" perception and cognition, and which are distinctive artifacts of deep learning-for artifacts like lens flares or Gibbs phenomena can be similarly useful for prediction, but are usually seen as obstacles to scientific theorizing. Thus, machine learning researchers urgently need to develop a theory of artifacts for deep neural networks, and I conclude by sketching some initial directions for this area of research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑