论文标题
可保证的人类风格的感知体系结构
A Safety Assurable Human-Inspired Perception Architecture
论文作者
论文摘要
尽管使用深神经网络（DNN）基于人工智能的感知（AIP）已接近人类水平的表现，但其众所周知的局限性是对自主应用所需的安全保证的障碍。这些包括对对抗性输入的脆弱性，无法处理新的输入和非解剖性。在解决这些局限性方面的研究中，在本文中，我们认为需要采取根本不同的方法来解决它们。受到人类认知的双重过程模型的启发，其中1型思维是快速且无意识的，而2型思维则缓慢并且基于有意识的推理，我们为安全AIP提出了双重过程体系结构。我们回顾了有关人类如何解决最简单的非平凡感知问题，图像分类的研究，并为此任务绘制相应的AIP体系结构。我们认为，这种体系结构可以提供一种系统的方法来解决使用DNNS的AIP局限性，并提供保证人类水平绩效及其他方法的方法。最后，我们讨论了现有工作可能已经解决了架构的哪些组成部分以及将来的工作。
Although artificial intelligence-based perception (AIP) using deep neural networks (DNN) has achieved near human level performance, its well-known limitations are obstacles to the safety assurance needed in autonomous applications. These include vulnerability to adversarial inputs, inability to handle novel inputs and non-interpretability. While research in addressing these limitations is active, in this paper, we argue that a fundamentally different approach is needed to address them. Inspired by dual process models of human cognition, where Type 1 thinking is fast and non-conscious while Type 2 thinking is slow and based on conscious reasoning, we propose a dual process architecture for safe AIP. We review research on how humans address the simplest non-trivial perception problem, image classification, and sketch a corresponding AIP architecture for this task. We argue that this architecture can provide a systematic way of addressing the limitations of AIP using DNNs and an approach to assurance of human-level performance and beyond. We conclude by discussing what components of the architecture may already be addressed by existing work and what remains future work.
