arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07083cs.LG
收藏

识别和利用可靠的深度学习结构

Identifying and Exploiting Structures for Reliable Deep Learning

Amartya Sanyal

摘要:

最近,深度学习研究在包括计算机视觉、自然语言处理和强化学习在内的广泛任务中取得了令人印象深刻的快速进展。这些系统的非凡性能往往给人一种印象,即它们可以用来彻底改变我们的生活。然而,正如最近的研究所指出的,这些系统存在几个问题,使它们在现实世界中使用时不可靠,包括易受对抗攻击的影响(Szegedy等人。[248]),记忆噪音的倾向(Zhang et al. [292]),对错误的预测过于自信(误校准)(Guo等人。[99]),以及不适合处理私人数据(Gilad-Bachrach等人。[88])。在这篇论文中,我们详细研究了这些问题,调查了它们的原因,并提出了计算成本低的算法来减轻它们在实践中。为此,我们确定了深度神经网络中的结构,可以利用这些结构来减轻深度学习算法不可靠的上述原因。

英文摘要:

Deep learning research has recently witnessed an impressively fast-paced progress in a wide range of tasks including computer vision, natural language processing, and reinforcement learning. The extraordinary performance of these systems often gives the impression that they can be used to revolutionise our lives for the better. However, as recent works point out, these systems suffer from several issues that make them unreliable for use in the real world, including vulnerability to adversarial attacks (Szegedy et al. [248]), tendency to memorise noise (Zhang et al. [292]), being over-confident on incorrect predictions (miscalibration) (Guo et al. [99]), and unsuitability for handling private data (Gilad-Bachrach et al. [88]). In this thesis, we look at each of these issues in detail, investigate their causes, and propose computationally cheap algorithms for mitigating them in practice. To do this, we identify structures in deep neural networks that can be exploited to mitigate the above causes of unreliability of deep learning algorithms.

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。

↑