深度卷积神经网络中的数字表示

IF 2.8 3区 心理学 Q1 PSYCHOLOGY, MULTIDISCIPLINARY Journal of Pacific Rim Psychology Pub Date : 2021-01-01 DOI:10.1177/18344909211012613
Cihua Zhou, Wei Xu, Yujie Liu, Zhichao Xue, Rui Chen, Ke Zhou, Jia Liu
{"title":"深度卷积神经网络中的数字表示","authors":"Cihua Zhou, Wei Xu, Yujie Liu, Zhichao Xue, Rui Chen, Ke Zhou, Jia Liu","doi":"10.1177/18344909211012613","DOIUrl":null,"url":null,"abstract":"Enumerating objects in the environment (i.e., “number sense”) is crucial for survival in many animal species, and foundational for the construction of more abstract and complex mathematical knowledge in humans. Perhaps surprisingly, deep convolutional neural networks (DCNNs) spontaneously emerge a similar number sense even without any explicit training for numerosity estimation. However, little is known about how the number sense emerges, and the extent to which it is comparable with human number sense. Here, we examined whether the numerosity underestimation effect, a phenomenon indicating that numerosity perception acts upon the perceptual number rather than the physical number, can be observed in DCNNs. In a typical DCNN, AlexNet, we found that number-selective units at late layers operated on the perceptual number, like humans do. More importantly, this perceptual number sense did not emerge abruptly, rather developed progressively along the hierarchy in the DCNN, shifting from the physical number sense at early layers to perceptual number sense at late layers. Our finding hence provides important implications for the neural implementation of number sense in the human brain and advocates future research to determine whether the representation of numerosity also develops gradually along the human visual stream from physical number to perceptual number.","PeriodicalId":45049,"journal":{"name":"Journal of Pacific Rim Psychology","volume":null,"pages":null},"PeriodicalIF":2.8000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1177/18344909211012613","citationCount":"4","resultStr":"{\"title\":\"Numerosity representation in a deep convolutional neural network\",\"authors\":\"Cihua Zhou, Wei Xu, Yujie Liu, Zhichao Xue, Rui Chen, Ke Zhou, Jia Liu\",\"doi\":\"10.1177/18344909211012613\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Enumerating objects in the environment (i.e., “number sense”) is crucial for survival in many animal species, and foundational for the construction of more abstract and complex mathematical knowledge in humans. Perhaps surprisingly, deep convolutional neural networks (DCNNs) spontaneously emerge a similar number sense even without any explicit training for numerosity estimation. However, little is known about how the number sense emerges, and the extent to which it is comparable with human number sense. Here, we examined whether the numerosity underestimation effect, a phenomenon indicating that numerosity perception acts upon the perceptual number rather than the physical number, can be observed in DCNNs. In a typical DCNN, AlexNet, we found that number-selective units at late layers operated on the perceptual number, like humans do. More importantly, this perceptual number sense did not emerge abruptly, rather developed progressively along the hierarchy in the DCNN, shifting from the physical number sense at early layers to perceptual number sense at late layers. Our finding hence provides important implications for the neural implementation of number sense in the human brain and advocates future research to determine whether the representation of numerosity also develops gradually along the human visual stream from physical number to perceptual number.\",\"PeriodicalId\":45049,\"journal\":{\"name\":\"Journal of Pacific Rim Psychology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2021-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1177/18344909211012613\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Pacific Rim Psychology\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://doi.org/10.1177/18344909211012613\",\"RegionNum\":3,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PSYCHOLOGY, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Pacific Rim Psychology","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1177/18344909211012613","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHOLOGY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 4

摘要

列举环境中的物体(即“数感”)对许多动物物种的生存至关重要,也是人类构建更抽象、更复杂的数学知识的基础。也许令人惊讶的是,深度卷积神经网络(DCNNs)即使没有任何明确的数字估计训练,也会自发地产生类似的数字感。然而,关于数字感是如何产生的,以及它与人类数字感的可比性的程度,人们知之甚少。在这里,我们研究了数字低估效应,即数字感知作用于感知数字而不是物理数字的现象,是否可以在DCNNs中观察到。在典型的DCNN AlexNet中,我们发现后期层的数字选择单元像人类一样对感知数字进行操作。更重要的是,这种感性数字感并不是突然出现的,而是沿着DCNN的层次结构逐步发展的,从早期的物理数字感转变为后期的感性数字感。因此,我们的发现为人类大脑中数感的神经实现提供了重要的启示,并倡导未来的研究,以确定数的表征是否也沿着人类视觉流从物理数到感知数逐渐发展。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Numerosity representation in a deep convolutional neural network
Enumerating objects in the environment (i.e., “number sense”) is crucial for survival in many animal species, and foundational for the construction of more abstract and complex mathematical knowledge in humans. Perhaps surprisingly, deep convolutional neural networks (DCNNs) spontaneously emerge a similar number sense even without any explicit training for numerosity estimation. However, little is known about how the number sense emerges, and the extent to which it is comparable with human number sense. Here, we examined whether the numerosity underestimation effect, a phenomenon indicating that numerosity perception acts upon the perceptual number rather than the physical number, can be observed in DCNNs. In a typical DCNN, AlexNet, we found that number-selective units at late layers operated on the perceptual number, like humans do. More importantly, this perceptual number sense did not emerge abruptly, rather developed progressively along the hierarchy in the DCNN, shifting from the physical number sense at early layers to perceptual number sense at late layers. Our finding hence provides important implications for the neural implementation of number sense in the human brain and advocates future research to determine whether the representation of numerosity also develops gradually along the human visual stream from physical number to perceptual number.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Pacific Rim Psychology
Journal of Pacific Rim Psychology PSYCHOLOGY, MULTIDISCIPLINARY-
CiteScore
4.00
自引率
0.00%
发文量
12
审稿时长
20 weeks
期刊最新文献
Sleep spindles consolidate declarative memory with tags: A meta-analysis of adult data Self-compassion as a factor in the deradicalisation of extremist offenders Impact of the COVID-19 epidemic on collectivism and individualism in China: A study of Weibo users You are worth it: Social support buffered the relation between impostor syndrome and suicidal ideation Effect of critical thinking disposition on employee innovative behavior: A meta-theory of personality perspective
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1