The Dimensions of dimensionality.

IF 16.7 1区 心理学 Q1 BEHAVIORAL SCIENCES
Brett D Roads, Bradley C Love
{"title":"The Dimensions of dimensionality.","authors":"Brett D Roads, Bradley C Love","doi":"10.1016/j.tics.2024.07.005","DOIUrl":null,"url":null,"abstract":"<p><p>Cognitive scientists often infer multidimensional representations from data. Whether the data involve text, neuroimaging, neural networks, or human judgments, researchers frequently infer and analyze latent representational spaces (i.e., embeddings). However, the properties of a latent representation (e.g., prediction performance, interpretability, compactness) depend on the inference procedure, which can vary widely across endeavors. For example, dimensions are not always globally interpretable and the dimensionality of different embeddings may not be readily comparable. Moreover, the dichotomy between multidimensional spaces and purportedly richer representational formats, such as graph representations, is misleading. We review what the different notions of dimension in cognitive science imply for how these latent representations should be used and interpreted.</p>","PeriodicalId":49417,"journal":{"name":"Trends in Cognitive Sciences","volume":null,"pages":null},"PeriodicalIF":16.7000,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Trends in Cognitive Sciences","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1016/j.tics.2024.07.005","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BEHAVIORAL SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Cognitive scientists often infer multidimensional representations from data. Whether the data involve text, neuroimaging, neural networks, or human judgments, researchers frequently infer and analyze latent representational spaces (i.e., embeddings). However, the properties of a latent representation (e.g., prediction performance, interpretability, compactness) depend on the inference procedure, which can vary widely across endeavors. For example, dimensions are not always globally interpretable and the dimensionality of different embeddings may not be readily comparable. Moreover, the dichotomy between multidimensional spaces and purportedly richer representational formats, such as graph representations, is misleading. We review what the different notions of dimension in cognitive science imply for how these latent representations should be used and interpreted.

维度的维度。
认知科学家经常从数据中推断多维表征。无论数据涉及文本、神经影像、神经网络还是人类判断,研究人员都会经常推断和分析潜在表征空间(即嵌入)。然而,潜在表征的属性(如预测性能、可解释性、紧凑性)取决于推理过程,而推理过程在不同的研究中可能会有很大差异。例如,维度并不总是全局可解释的,而且不同嵌入式的维度可能不容易比较。此外,将多维空间与所谓更丰富的表征格式(如图表征)对立起来会产生误导。我们回顾了认知科学中不同的维度概念对如何使用和解释这些潜在表征的影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Trends in Cognitive Sciences
Trends in Cognitive Sciences 医学-行为科学
CiteScore
27.90
自引率
1.50%
发文量
156
审稿时长
6-12 weeks
期刊介绍: Essential reading for those working directly in the cognitive sciences or in related specialist areas, Trends in Cognitive Sciences provides an instant overview of current thinking for scientists, students and teachers who want to keep up with the latest developments in the cognitive sciences. The journal brings together research in psychology, artificial intelligence, linguistics, philosophy, computer science and neuroscience. Trends in Cognitive Sciences provides a platform for the interaction of these disciplines and the evolution of cognitive science as an independent field of study.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信