气候变化领域集成服务门户(CCPortal): Communicating artificial neural networks develop efficient color-naming systems

CCPortal

DOI	10.1073/pnas.2016569118
	Communicating artificial neural networks develop efficient color-naming systems
	Chaabouni R.; Kharitonov E.; Dupoux E.; Baroni M.
发表日期	2021
ISSN	00278424
卷号	118 期号:12
英文摘要	Words categorize the semantic fields they refer to in ways that maximize communication accuracy while minimizing complexity. Focusing on the well-studied color domain, we show that artificial neural networks trained with deep-learning techniques to play a discrimination game develop communication systems whose distribution on the accuracy/complexity plane closely matches that of human languages. The observed variation among emergent color-naming systems is explained by different degrees of discriminative need, of the sort that might also characterize different human communities. Like human languages, emergent systems show a preference for relatively low-complexity solutions, even at the cost of imperfect communication. We demonstrate next that the nature of the emergent systems crucially depends on communication being discrete (as is human word usage). When continuous message passing is allowed, emergent systems become more complex and eventually less efficient. Our study suggests that efficient semantic categorization is a general property of discrete communication systems, not limited to human language. It suggests moreover that it is exactly the discrete nature of such systems that, acting as a bottleneck, pushes them toward low complexity and optimal efficiency. © 2021 National Academy of Sciences. All rights reserved.
英文关键词	Color-naming systems; Efficiency of human language; Language emergence in artificial neural networks
语种	英语
scopus关键词	article; artificial neural network; deep learning; human; human experiment; language
来源期刊	Proceedings of the National Academy of Sciences of the United States of America
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/180127
作者单位	Facebook AI Research, Paris, 75002, France; Cognitive Machine Learning, ENS - EHESS - PSL Research University, CNRS - INRIA, Paris, 75012, France; Institució Catalana de Recerca i Estudis Avançats, Barcelona, 08010, Spain
推荐引用方式 GB/T 7714	Chaabouni R.,Kharitonov E.,Dupoux E.,et al. Communicating artificial neural networks develop efficient color-naming systems[J],2021,118(12).
APA	Chaabouni R.,Kharitonov E.,Dupoux E.,&Baroni M..(2021).Communicating artificial neural networks develop efficient color-naming systems.Proceedings of the National Academy of Sciences of the United States of America,118(12).
MLA	Chaabouni R.,et al."Communicating artificial neural networks develop efficient color-naming systems".Proceedings of the National Academy of Sciences of the United States of America 118.12(2021).