黑暗，超越深度：一个具有人类常识的认知AI的范式转变
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
摘要：
深度学习的最新进展基本上是基于“小任务的大数据”范式，在这种范式下，使用大量数据来训练用于单个窄任务的分类器。在本文中，我们呼吁改变这种范式。具体来说，我们提出了一个“小数据大任务”的范例，其中一个单一的人工智能（AI）系统面临的挑战是发展“常识”，使其能够解决各种各样的任务很少训练数据。我们通过回顾综合了机器和人类视觉最近突破的常识模型来说明这种新范式的潜在力量。我们将功能、物理、意图、因果和效用（FPICU）确定为具有人类常识的认知AI的五个核心领域。当作为一个统一的概念时，FPICU关注的是“为什么”和“如何”的问题，超越了理解视觉的主导框架“什么”和“哪里”。它们在像素方面是不可见的，但仍然推动着视觉场景的创建、维护和开发。因此，我们称它们为视觉的“暗物质”。正如我们的宇宙不能仅仅通过研究可观察物质来理解一样，我们认为，如果不研究FPICU，就不能理解视觉。我们展示了这种观点的力量，通过展示如何观察和应用FPICU与很少的训练数据来解决各种具有挑战性的任务，包括工具使用，规划，效用推理和社会学习，开发具有人类常识的认知AI系统。总之，我们认为下一代人工智能必须接受“黑暗”的人类常识来解决新的任务。
英文摘要：
Recent progress in deep learning is essentially based on a "big data for small tasks" paradigm, under which massive amounts of data are used to train a classifier for a single narrow task. In this paper, we call for a shift that flips this paradigm upside down. Specifically, we propose a "small data for big tasks" paradigm, wherein a single artificial intelligence (AI) system is challenged to develop "common sense", enabling it to solve a wide range of tasks with little training data. We illustrate the potential power of this new paradigm by reviewing models of common sense that synthesize recent breakthroughs in both machine and human vision. We identify functionality, physics, intent, causality, and utility (FPICU) as the five core domains of cognitive AI with humanlike common sense. When taken as a unified concept, FPICU is concerned with the questions of "why" and "how", beyond the dominant "what" and "where" framework for understanding vision. They are invisible in terms of pixels but nevertheless drive the creation, maintenance, and development of visual scenes. We therefore coin them the "dark matter" of vision. Just as our universe cannot be understood by merely studying observable matter, we argue that vision cannot be understood without studying FPICU. We demonstrate the power of this perspective to develop cognitive AI systems with humanlike common sense by showing how to observe and apply FPICU with little training data to solve a wide range of challenging tasks, including tool use, planning, utility inference, and social learning. In summary, we argue that the next generation of AI must embrace "dark" humanlike common sense for solving novel tasks.
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。
