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

by   Yixin Zhu, et al.

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.


page 13

page 14

page 19

page 20

page 23

page 26

page 28

page 29


Machine Common Sense Concept Paper

This paper summarizes some of the technical background, research ideas, ...

Conscious AI

Recent advances in artificial intelligence (AI) have achieved human-scal...

Adaptive cognitive fit: Artificial intelligence augmented management of information facets and representations

Explosive growth in big data technologies and artificial intelligence [A...

Fantastic Data and How to Query Them

It is commonly acknowledged that the availability of the huge amount of ...

Data Cleaning for Accurate, Fair, and Robust Models: A Big Data - AI Integration Approach

The wide use of machine learning is fundamentally changing the software ...

A Glimpse in ChatGPT Capabilities and its impact for AI research

Large language models (LLMs) have recently become a popular topic in the...

Toward a New Science of Common Sense

Common sense has always been of interest in AI, but has rarely taken cen...

Please sign up or login with your details

Forgot password? Click here to reset