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

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...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	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
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Elsevier 2020-03-01
Schriftenreihe:	Engineering
Online-Zugang:	http://www.sciencedirect.com/science/article/pii/S2095809920300345
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!