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.
翻译:深层的学习研究最近目睹了在一系列广泛任务(包括计算机视觉、自然语言处理和强化学习)方面取得令人印象深刻的快速进展。这些系统的出色表现往往给人一种印象,即它们可以用来使我们的生活变得更好地革命。然而,正如最近的著作指出的,这些系统存在若干问题,使其在现实世界中的使用不可靠,包括易受对抗性攻击(Szegedy等人,[248])、回忆起噪音的倾向(Zhang等人,[292]),过度相信错误预测(误差)(Guo等人,[99])和处理私人数据的不适宜性(Gilad-Bachrach等人,[88])。在这个论文中,我们详细研究其中的每一个问题,调查其原因,并提出在实际中减轻这些原因的计算廉价算法。为了做到这一点,我们确定了深神经网络的结构,可以用来减轻深层学习算法不可靠的上述原因。