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

By Yixin Zhu, Tao Gao, Lifeng Fan, Siyuan Huang, Mark Edmonds, Hangxin Liu, Feng Gao, Chi Zhang, Siyuan Qi, Ying Nian Wu and 2 more. 2020

152 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Cognitive Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jiafei Duan
2. Samson Yu
3. Cheston Tan
4. Siyuan Huang
5. Song-Chun Zhu
6. Yining Hong
7. Daniel Ciao
8. Qing Li

In Cognitive Neuroscience

1. Song-Chun Zhu
2. Yining Hong
3. Cheston Tan
4. Siyuan Huang
5. Daniel Ciao
6. Qing Li

Citations in the corpus

• A Survey of Embodied AI: From Simulators to Research Tasks (2021, background): “The ability to have fine-grained manipulative interactions with functional objects in the embodied AI simulators are crucial in replicating human-level interactions with real-world objects [129].”
• An Embodied Generalist Agent in 3D World (2023, unknown): “Building one generalist model that can handle comprehensive tasks like humans has been a long-existing pursuit in artificial intelligence and neuroscience (Lake et al., 2015; 2017; Zhu et al., 2020; Mountcastle, 1979; Schmid-huber, 2018; Huang et al., 2022a).”
• Learning by Fixing: Solving Math Word Problems with Weak Supervision (2020, background): “Recently, there emerges various question-answering tasks that require human-like reasoning abilities (Qi et al. 2015; Tu et al. 2014; Zhang et al. 2019; Dua et al. 2019; Hong et al. 2019; Zhu et al. 2020; Zhang et al. 2020b; Li et al. 2020b; Yu et al. 2020).”