黑暗，超越深度：具有人类常识的认知人工智能的范式转变（CS AI）---刘持诚

最近在深度学习方面的进展基本上是基于“小任务大数据”范式，在这种范式下，海量的数据被用来训练一个分类器来完成单一的狭义任务。在这篇文章中，我们呼吁颠覆改变这种范式。具体来说，我们提出了一种“小数据大任务”的范式，在这种范式下，单一的人工智能（AI）系统面临着开发“常识”的挑战，使其能够用很少的训练数据解决各种任务。我们通过回顾综合了最近在机器视觉和人类视觉方面的突破，说明了这种新范式的潜在力量。我们将功能、物理、意图、因果关系和实用性（FPICU）确定为认知 AI 的五个核心领域，并将其作为具有类似人类常识的认知 AI 的核心领域。当作为一个统一的概念，FPICU 关注的是 "why" 和 "how" 的问题，超越了主流的 "what" 和 "where" 的框架来理解视觉。它们在像素方面是看不见的，但却推动着视觉场景的产生、维护和发展。因此，我们把它们称为视觉的“暗物质”。正如我们的宇宙不能仅仅通过研究可观测到的物质来理解，我们认为，不研究 FPICU 就不能理解视觉。我们通过展示如何用很少的训练数据来观察和应用 FPICU 来解决各种具有挑战性的任务，包括工具使用、规划、实用性推理和社会化学习等，来证明这个观点在开发具有人类相似常识的认知 AI 系统方面的力量。综上所述，我们认为，下一代人工智能必须拥抱“黑暗 ”的，类似人类的常识来解决新颖的任务。

原文题目：Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense

原文：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.

原文作者：Yixin Zhu, Tao Gao, Lifeng Fan, Siyuan Huang, Mark Edmonds, Hangxin Liu, Feng Gao, Chi Zhang, Siyuan Qi, Ying Nian Wu, Joshua B. Tenenbaum, Song-Chun Zhu

原文地址：https://arxiv.org/abs/2004.09044v1