CCPortal
DOI10.1073/pnas.2016569118
Communicating artificial neural networks develop efficient color-naming systems
Chaabouni R.; Kharitonov E.; Dupoux E.; Baroni M.
发表日期2021
ISSN00278424
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).
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Chaabouni R.]的文章
[Kharitonov E.]的文章
[Dupoux E.]的文章
百度学术
百度学术中相似的文章
[Chaabouni R.]的文章
[Kharitonov E.]的文章
[Dupoux E.]的文章
必应学术
必应学术中相似的文章
[Chaabouni R.]的文章
[Kharitonov E.]的文章
[Dupoux E.]的文章
相关权益政策
暂无数据
收藏/分享

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。