Next Generation Psychological Embeddings

下一代心理嵌入

基本信息

  • 批准号:
    ES/W007347/1
  • 负责人:
  • 金额:
    $ 84.48万
  • 依托单位:
  • 依托单位国家:
    英国
  • 项目类别:
    Research Grant
  • 财政年份:
    2022
  • 资助国家:
    英国
  • 起止时间:
    2022 至 无数据
  • 项目状态:
    未结题

项目摘要

People have vast knowledge bases that allow them to represent relevant information about the world and act upon it. While there are specialist computer systems that best people in specific tasks, such as playing chess, humans are still the champions at being generalists. How do humans represent their rich knowledge so that they can appreciate similarities between objects, whether those similarities rest on superficial properties or deep connections, such as belonging to a shared biological category? It is a difficult question to answer that has both theoretical and practical ramifications. Understanding how people perceive the world is key to predicting and improving human behaviour. Likewise, building such representational or embedding spaces would provide a powerful tool for making AI systems more human-like.Standard techniques for inferring psychological representations have been in wide use since the 1950s, but are limited in important ways. Standard techniques are data hungry and computationally slow. As a consequence, these techniques do not work well with real-world problems that often contain more than a million items. We aim to help Psychology transition to large-scale modelling, which we hope leads to a revolution like that experienced a decade ago in machine learning and AI when those fields moved to large-scale datasets. Another limitation of standard techniques is that they can't detect or take advantage of the relationships between items in the representational space. For example, if people know that two breeds of dogs are both dogs, even if they differ in size, they use that structural knowledge when making inferences. Our modelling approaches can discover and use such conceptual relationships. Likewise, we can capture how different groups, who vary in their life experiences, may represent the world in slightly different ways. In doing so, we can capture the uniqueness of each human experience rather than force a one-size-fits-all approach on the data, which would be a kind of tyranny of the majority for data science and Psychology. Finally, our methods can be adapted to take advantage of different approaches to measuring similarity. Collectively, these limitations in standard approaches block the transfer of laboratory insights into real-world settings. While work has been done to address some of these limitations, no work has addressed all these limitations fully at once. We aim to do so at scale considering two databases of natural images (i.e., photographs) that each contain over a million images. Rather than offer an incremental advance, we aim to advance the state-of-the-art for representing spaces by more than an order of magnitude in size and improve the quality of the solution by capturing relations between images and groups of people as discussed above. We will make these resources and the tools publicly and freely available with guidance on how they can be extended to support others' work, whether it be in Psychology, Education, Human-Computer Interaction, AI, or other fields. Inferring psychological representations for these two large datasets will remove a long-standing hurdle in the research community, which should help machine learning and cognitive science researchers create better models of human cognition. This new framework and resource will make it possible to model differences between individuals, allowing us to better understand how different life experiences, such as measured by age, gender, and geographical location, impact how we think about the world.
人们拥有庞大的知识库,使他们能够表示有关世界的相关信息并据此采取行动。尽管有专业的计算机系统可以在特定任务(例如下国际象棋)中表现最好,但人类仍然是通才方面的冠军。人类如何表达他们丰富的知识,以便能够欣赏物体之间的相似性,无论这些相似性是基于表面属性还是深层联系,例如属于共享的生物类别?这是一个很难回答的问题,具有理论和实践影响。了解人们如何看待世界是预测和改善人类行为的关键。同样,构建此类表征或嵌入空间将为人工智能系统变得更加人性化提供强大的工具。自 20 世纪 50 年代以来,推断心理表征的标准技术一直在广泛使用,但在一些重要方面受到限制。标准技术需要大量数据且计算速度较慢。因此,这些技术不能很好地解决通常包含超过一百万个项目的现实问题。我们的目标是帮助心理学过渡到大规模建模,我们希望这会引发一场像十年前机器学习和人工智能领域转向大规模数据集时所经历的革命。标准技术的另一个限制是它们无法检测或利用表征空间中项目之间的关系。例如,如果人们知道两种狗都是狗,即使它们的大小不同,他们也会在进行推理时使用这种结构知识。我们的建模方法可以发现并使用这种概念关系。同样,我们可以捕捉到生活经历不同的不同群体如何以略有不同的方式代表世界。通过这样做,我们可以捕捉每个人类经历的独特性,而不是在数据上强制采用一刀切的方法,这对数据科学和心理学来说是一种多数人的暴政。最后,我们的方法可以适应利用不同的方法来测量相似性。总的来说,标准方法的这些局限性阻碍了实验室见解向现实世界环境的转移。虽然已经开展了一些工作来解决其中一些限制,但还没有任何工作能够立即完全解决所有这些限制。我们的目标是大规模地这样做,考虑到两个自然图像(即照片)数据库,每个数据库都包含超过一百万张图像。我们的目标不是提供渐进式的进步,而是将表示空间的最先进技术提高一个数量级以上,并通过捕获图像和人群之间的关系来提高解决方案的质量,如上所述。我们将公开免费提供这些资源和工具,并指导如何扩展它们以支持他人的工作,无论是在心理学、教育、人机交互、人工智能还是其他领域。推断这两个大型数据集的心理表征将消除研究界长期存在的障碍,这将有助于机器学习和认知科学研究人员创建更好的人类认知模型。这个新的框架和资源将使模拟个体之间的差异成为可能,使我们能够更好地理解不同的生活经历(例如以年龄、性别和地理位置衡量的生活经历)如何影响我们对世界的看法。

项目成果

期刊论文数量(6)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
You can't play 20 questions with nature and win redux
你无法与自然玩 20 个问题并赢得 redux
  • DOI:
    http://dx.10.1017/s0140525x23001747
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    29.3
  • 作者:
    Love B
  • 通讯作者:
    Love B
Modeling Similarity and Psychological Space
建模相似性和心理空间
  • DOI:
    http://dx.10.1146/annurev-psych-040323-115131
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    24.8
  • 作者:
    Roads B
  • 通讯作者:
    Roads B
A controller-peripheral architecture and costly energy principle for learning
控制器外设架构和昂贵的能源学习原理
  • DOI:
    10.1101/2023.01.16.524194
  • 发表时间:
    2023-08-12
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Xiaoliang Luo;Robert M. Mok;Brett D. Roads;B. Love
  • 通讯作者:
    B. Love
A too-good-to-be-true prior to reduce shortcut reliance.
一个好得令人难以置信的先决条件,以减少对捷径的依赖。
  • DOI:
    http://dx.10.1016/j.patrec.2022.12.010
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    5.1
  • 作者:
    Dagaev N
  • 通讯作者:
    Dagaev N
A multilevel account of hippocampal function in spatial and concept learning: Bridging models of behavior and neural assemblies.
海马在空间和概念学习中的功能的多层次解释:行为和神经组装的桥接模型。
  • DOI:
    http://dx.10.1126/sciadv.ade6903
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    13.6
  • 作者:
    Mok RM
  • 通讯作者:
    Mok RM
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Bradley Love其他文献

Human-in-the-loop mixup
人机交互混合
  • DOI:
    10.1109/access.2024.3365777
  • 发表时间:
    2024-09-13
  • 期刊:
  • 影响因子:
    3.9
  • 作者:
    Katherine M. Collins;Umang Bhatt;Weiyang Liu;Vihari Piratla;Bradley Love;Adrian Weller
  • 通讯作者:
    Adrian Weller
Using Artificial Intelligence to Improve the Accuracy of a Wrist-Worn, Noninvasive Glucose Monitor: A Pilot Study.
使用人工智能提高腕戴式无创血糖监测仪的准确性:一项试点研究。
  • DOI:
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    5
  • 作者:
    Muhammad Rafaqat Ali Qureshi;S. C. Bain;Stephen D Luzio;Consuelo Handy;Daniel J Fowles;Bradley Love;Kathie Wareham;Lucy Barlow;G. Dunseath;Joel Crane;Isamar Carrillo Masso;Julia A M Ryan;M. S. Chaudhry
  • 通讯作者:
    M. S. Chaudhry
Representational Alignment Supports Effective Machine Teaching
表征对齐支持有效的机器教学
  • DOI:
  • 发表时间:
    2024-06-06
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Ilia Sucholutsky;Katherine M. Collins;Maya Malaviya;Nori Jacoby;Weiyang Liu;T. Sumers;Michalis Korakakis;Umang Bhatt;Mark K. Ho;J. B. Tenenbaum;Bradley Love;Z. Pardos;Adrian Weller;Thomas L. Griffiths
  • 通讯作者:
    Thomas L. Griffiths
Food insecurity is positively related to overweight in women.
粮食不安全与女性超重呈正相关。
  • DOI:
    10.1093/jn/131.6.1738
  • 发表时间:
    2001-06-01
  • 期刊:
  • 影响因子:
    0
  • 作者:
    M. Townsend;J. Peerson;Bradley Love;C. Achterberg;S. Murphy
  • 通讯作者:
    S. Murphy
Noninvasive Continuous Glucose Monitoring With a Novel Wearable Dial Resonating Sensor: A Clinical Proof-of-Concept Study.
使用新型可穿戴表盘谐振传感器进行无创连续血糖监测:临床概念验证研究。
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    5
  • 作者:
    Consuelo Handy;M. S. Chaudhry;Muhammad Rafaqat Ali Qureshi;Bradley Love;John Shillingford;L. Plum;E. Zijlstra
  • 通讯作者:
    E. Zijlstra

Bradley Love的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Bradley Love', 18)}}的其他基金

CAREER: Flexible Learning Inside and Outside the Classroom
职业:课堂内外灵活的学习
  • 批准号:
    0349101
  • 财政年份:
    2004
  • 资助金额:
    $ 84.48万
  • 项目类别:
    Continuing Grant

相似国自然基金

新一代动态植被模型CLM5(FATES)研究未来变暖下东北地区植被反馈作用
  • 批准号:
    42305041
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
基于新一代深度概率模型的智能分子生成新方法及其应用研究
  • 批准号:
    82373791
  • 批准年份:
    2023
  • 资助金额:
    49 万元
  • 项目类别:
    面上项目
面向理想物理性能分布的新一代高性能装配技术基础理论与方法
  • 批准号:
    52335011
  • 批准年份:
    2023
  • 资助金额:
    230 万元
  • 项目类别:
    重点项目
新一代非共线性密度泛函及应用
  • 批准号:
    22373004
  • 批准年份:
    2023
  • 资助金额:
    50 万元
  • 项目类别:
    面上项目
创制可转化利用木质素基酚类化合物的新一代产油红酵母
  • 批准号:
    22308350
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目

相似海外基金

UEM Collaborative Research Ethics Education Program
UEM 合作研究伦理教育计划
  • 批准号:
    10755523
  • 财政年份:
    2023
  • 资助金额:
    $ 84.48万
  • 项目类别:
CSRD Research Career Scientist Award Application
CSRD研究职业科学家奖申请
  • 批准号:
    10701136
  • 财政年份:
    2023
  • 资助金额:
    $ 84.48万
  • 项目类别:
Generating Research Opportunities Within Statistics at Fred Hutch (GROWS@FredHutch)
在 Fred Hutch 的统计领域创造研究机会 (GROWS@FredHutch)
  • 批准号:
    10627415
  • 财政年份:
    2023
  • 资助金额:
    $ 84.48万
  • 项目类别:
Dissecting the functional relevance of unique subpopulations of striatal dopamine receptors in opioid use disorder
剖析纹状体多巴胺受体独特亚群在阿片类药物使用障碍中的功能相关性
  • 批准号:
    10806330
  • 财政年份:
    2023
  • 资助金额:
    $ 84.48万
  • 项目类别:
next-generation sequencing approaches to identify genotype-phenotype relationships during miRNA tuning of neural crest osteogenesis
新一代测序方法可识别神经嵴成骨过程中 miRNA 调节过程中的基因型与表型关系
  • 批准号:
    10579800
  • 财政年份:
    2023
  • 资助金额:
    $ 84.48万
  • 项目类别:
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了