RI: Small: CompCog: Leveraging Deep Neural Networks for Understanding Human Cognition
RI:小型:CompCog:利用深度神经网络理解人类认知
基本信息
- 批准号:1932035
- 负责人:
- 金额:$ 18.58万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2019
- 资助国家:美国
- 起止时间:2019-03-01 至 2021-07-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
The last few years have seen significant breakthroughs in artificial intelligence and machine learning, resulting in systems that approach or even exceed human performance in interpreting pictures and words. This project explores the implications of these breakthroughs for understanding how the human mind works. Focusing on artificial neural networks, a key technology behind many recent breakthroughs that is capable of discovering novel representations for complex stimuli, the project has two goals. First, assessing the degree of correspondence between human and machine learning by examining whether the pictures or words that are similar in the representations discovered by neural network models are also judged to be similar by people. Second, developing methods for increasing this correspondence, with the goal of being able to use neural network representations to generate good predictions about how people learn and form categories using real images or text.This research project will answer basic scientific questions about how the representations discovered by contemporary neural networks relate to human cognition. It will then explore what architectures and training regimes produce representations with these properties. In addition, the project will address the methodological question of how one can modify these representations to produce better alignment with human cognition. Answering this question will lead to powerful new tools for making models of human behavior in naturalistic contexts, leveraging the latest results in machine learning to broaden the scope of experimental research in cognitive science. By building stronger links between human and machine learning, this project will have implications for both fields. Even if current neural network systems turn out to differ significantly from human learning, they provide state-of-the-art representations for images and text that can be used as a starting point for developing better accounts of human representations. By discovering the ways in which the representations learned by artificial neural networks differ from those of humans, one can identify new algorithms and training methods that will result in a closer alignment. Since human beings remain the best examples available of systems that can solve certain problems, such an alignment offers a path toward expanding the capacities of current artificial intelligence systems and making them more interpretable by people, which is critical in settings that require human-machine interaction.
在过去的几年里,人工智能和机器学习取得了重大突破,导致系统在解释图片和文字方面接近甚至超过人类的表现。这个项目探索了这些突破对理解人类大脑如何工作的影响。该项目专注于人工神经网络,这是最近许多突破背后的关键技术,能够发现复杂刺激的新表示法,该项目有两个目标。首先,通过检测神经网络模型发现的表示相似的图片或单词是否也被人类判断为相似,来评估人类和机器学习之间的对应程度。第二,开发增加这种一致性的方法,目标是能够使用神经网络表征来生成关于人们如何使用真实图像或文本学习和形成类别的良好预测。这项研究项目将回答关于当代神经网络发现的表征如何与人类认知相关的基本科学问题。然后,它将探索哪些体系结构和培训制度产生具有这些属性的表示。此外,该项目将解决如何修改这些表示法以使其更符合人类认知的方法论问题。回答这个问题将带来强大的新工具,用于在自然环境中建立人类行为模型,利用机器学习的最新结果来扩大认知科学的实验研究范围。通过在人类和机器学习之间建立更紧密的联系,该项目将对这两个领域产生影响。即使目前的神经网络系统被证明与人类的学习显著不同,它们也提供了最先进的图像和文本表示法,可以作为开发更好的人类表示法的起点。通过发现人工神经网络学习的表示与人类的表示不同的方式,人们可以确定新的算法和训练方法,从而导致更紧密的比对。由于人类仍然是可以解决某些问题的系统的最佳例子,这样的结合提供了一条途径,可以扩展当前人工智能系统的能力,使它们更容易被人解释,这在需要人机交互的环境中至关重要。
项目成果
期刊论文数量(8)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
End-to-end Deep Prototype and Exemplar Models for Predicting Human Behavior
- DOI:
- 发表时间:2020-07
- 期刊:
- 影响因子:0
- 作者:Pulkit Singh;Joshua C. Peterson;Ruairidh M. Battleday;T. Griffiths
- 通讯作者:Pulkit Singh;Joshua C. Peterson;Ruairidh M. Battleday;T. Griffiths
Extracting Low-Dimensional Psychological Representations from Convolutional Neural Networks
- DOI:10.1111/cogs.13226
- 发表时间:2023-01-01
- 期刊:
- 影响因子:2.5
- 作者:Jha, Aditi;Peterson, Joshua C.;Griffiths, Thomas L.
- 通讯作者:Griffiths, Thomas L.
Learning deep taxonomic priors for concept learning from few positive examples
从几个积极的例子中学习概念学习的深度分类学先验
- DOI:
- 发表时间:2019
- 期刊:
- 影响因子:0
- 作者:Grant, Erin;Peterson, Joshua C;Griffiths, Thomas L
- 通讯作者:Griffiths, Thomas L
Parallelograms revisited: Exploring the limitations of vector space models for simple analogies
- DOI:10.1016/j.cognition.2020.104440
- 发表时间:2020-08
- 期刊:
- 影响因子:3.4
- 作者:Joshua C. Peterson;Dawn Chen;T. Griffiths
- 通讯作者:Joshua C. Peterson;Dawn Chen;T. Griffiths
Using large-scale experiments and machine learning to discover theories of human decision-making
- DOI:10.1126/science.abe2629
- 发表时间:2021-06-11
- 期刊:
- 影响因子:56.9
- 作者:Peterson, Joshua C.;Bourgin, David D.;Griffiths, Thomas L.
- 通讯作者:Griffiths, Thomas L.
{{
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 }}
Thomas Griffiths其他文献
Slicing the Silence: Voyaging to Antarctica
打破沉默:南极洲航行
- DOI:
10.5860/choice.45-6922 - 发表时间:
2007 - 期刊:
- 影响因子:0.3
- 作者:
Thomas Griffiths - 通讯作者:
Thomas Griffiths
Inland shell midden site-formation: Investigation into a late Pleistocene to early Holocene midden from Tràng An, Northern Vietnam
内陆贝冢遗址形成:越南北部长安的更新世晚期至全新世早期贝冢调查
- DOI:
10.1016/j.quaint.2010.01.025 - 发表时间:
2011 - 期刊:
- 影响因子:2.2
- 作者:
R. Rabett;J. Appleby;A. Blyth;L. Farr;Athanasia Gallou;Thomas Griffiths;Jason D. Hawkes;David W. Marcus;L. Marlow;Mike W. Morley;N. C. Tâń;Nguyêń Van Son;K. Penkman;T. Reynolds;C. Stimpson;K. Szabó - 通讯作者:
K. Szabó
Information extraction from multimedia web documents: an open-source platform and testbed
从多媒体网络文档中提取信息:开源平台和测试床
- DOI:
10.1007/s13735-014-0051-2 - 发表时间:
2014 - 期刊:
- 影响因子:5.6
- 作者:
D. Dupplaw;Michael Matthews;Richard Johansson;G. Boato;Andrea Costanzo;M. Fontani;E. Minack;Elena Demidova;Roi Blanco;Thomas Griffiths;P. Lewis;Jonathon S. Hare;Alessandro Moschitti - 通讯作者:
Alessandro Moschitti
Ecology and Empire: Environmental History of Settler Societies
生态与帝国:定居者社会的环境史
- DOI:
10.2307/3985187 - 发表时间:
2017 - 期刊:
- 影响因子:0
- 作者:
Thomas Griffiths;L. Robin - 通讯作者:
L. Robin
Performance Characterisation and Optimisation of a Building Integrated Photovoltaic (BIPV) System in a Maritime Climate
海洋气候下建筑一体化光伏 (BIPV) 系统的性能表征和优化
- DOI:
10.5334/fce.62 - 发表时间:
2019 - 期刊:
- 影响因子:0
- 作者:
D. Brennan;C. White;M. Barclay;Thomas Griffiths;Richard P. Lewis - 通讯作者:
Richard P. Lewis
Thomas Griffiths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('Thomas Griffiths', 18)}}的其他基金
Collaborative Research: CompCog: RI: Medium: Understanding human planning through AI-assisted analysis of a massive chess dataset
合作研究:CompCog:RI:中:通过人工智能辅助分析海量国际象棋数据集了解人类规划
- 批准号:
2312373 - 财政年份:2023
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
RAPID: The effect of a crisis on intertemporal choice
RAPID:危机对跨期选择的影响
- 批准号:
2026984 - 财政年份:2020
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
CompCog: Helping people make more future-minded decisions using optimal gamification
CompCog:利用最佳游戏化帮助人们做出更具前瞻性的决策
- 批准号:
1930720 - 财政年份:2019
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
CompCog: Helping people make more future-minded decisions using optimal gamification
CompCog:利用最佳游戏化帮助人们做出更具前瞻性的决策
- 批准号:
1757269 - 财政年份:2018
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
RI: Small: CompCog: Leveraging Deep Neural Networks for Understanding Human Cognition
RI:小型:CompCog:利用深度神经网络理解人类认知
- 批准号:
1718550 - 财政年份:2017
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
Testing evolutionary hypotheses through large-scale behavioral simulations
通过大规模行为模拟测试进化假设
- 批准号:
1456709 - 财政年份:2015
- 资助金额:
$ 18.58万 - 项目类别:
Continuing Grant
The dynamics of updating and transmitting individual and collective memories
更新和传递个人和集体记忆的动态
- 批准号:
1408652 - 财政年份:2014
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
Diagnosing misconceptions about algebra using Bayesian inverse reinforcement learning
使用贝叶斯逆强化学习诊断代数的误解
- 批准号:
1420732 - 财政年份:2014
- 资助金额:
$ 18.58万 - 项目类别:
Continuing Grant
Data on the mind: Center for Data-Intensive Psychological Science
心灵数据:数据密集型心理科学中心
- 批准号:
1338541 - 财政年份:2013
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
CAREER: Connecting Human and Machine Learning through Probabilistic Models of Cognition
职业:通过概率认知模型连接人类和机器学习
- 批准号:
0845410 - 财政年份:2009
- 资助金额:
$ 18.58万 - 项目类别:
Continuing Grant
相似国自然基金
昼夜节律性small RNA在血斑形成时间推断中的法医学应用研究
- 批准号:
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
tRNA-derived small RNA上调YBX1/CCL5通路参与硼替佐米诱导慢性疼痛的机制研究
- 批准号:n/a
- 批准年份:2022
- 资助金额:10.0 万元
- 项目类别:省市级项目
Small RNA调控I-F型CRISPR-Cas适应性免疫性的应答及分子机制
- 批准号:32000033
- 批准年份:2020
- 资助金额:24.0 万元
- 项目类别:青年科学基金项目
Small RNAs调控解淀粉芽胞杆菌FZB42生防功能的机制研究
- 批准号:31972324
- 批准年份:2019
- 资助金额:58.0 万元
- 项目类别:面上项目
变异链球菌small RNAs连接LuxS密度感应与生物膜形成的机制研究
- 批准号:81900988
- 批准年份:2019
- 资助金额:21.0 万元
- 项目类别:青年科学基金项目
肠道细菌关键small RNAs在克罗恩病发生发展中的功能和作用机制
- 批准号:31870821
- 批准年份:2018
- 资助金额:56.0 万元
- 项目类别:面上项目
基于small RNA 测序技术解析鸽分泌鸽乳的分子机制
- 批准号:31802058
- 批准年份:2018
- 资助金额:26.0 万元
- 项目类别:青年科学基金项目
Small RNA介导的DNA甲基化调控的水稻草矮病毒致病机制
- 批准号:31772128
- 批准年份:2017
- 资助金额:60.0 万元
- 项目类别:面上项目
基于small RNA-seq的针灸治疗桥本甲状腺炎的免疫调控机制研究
- 批准号:81704176
- 批准年份:2017
- 资助金额:20.0 万元
- 项目类别:青年科学基金项目
水稻OsSGS3与OsHEN1调控small RNAs合成及其对抗病性的调节
- 批准号:91640114
- 批准年份:2016
- 资助金额:85.0 万元
- 项目类别:重大研究计划
相似海外基金
CSR: Small: Leveraging Physical Side-Channels for Good
CSR:小:利用物理侧通道做好事
- 批准号:
2312089 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
NeTS: Small: NSF-DST: Modernizing Underground Mining Operations with Millimeter-Wave Imaging and Networking
NeTS:小型:NSF-DST:利用毫米波成像和网络实现地下采矿作业现代化
- 批准号:
2342833 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
CPS: Small: NSF-DST: Autonomous Operations of Multi-UAV Uncrewed Aerial Systems using Onboard Sensing to Monitor and Track Natural Disaster Events
CPS:小型:NSF-DST:使用机载传感监测和跟踪自然灾害事件的多无人机无人航空系统自主操作
- 批准号:
2343062 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
Collaborative Research: FET: Small: Reservoir Computing with Ion-Channel-Based Memristors
合作研究:FET:小型:基于离子通道忆阻器的储层计算
- 批准号:
2403559 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
オミックス解析を用いたブドウ球菌 small colony variants の包括的特徴づけ
使用组学分析全面表征葡萄球菌小菌落变体
- 批准号:
24K13443 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
AF: Small: Problems in Algorithmic Game Theory for Online Markets
AF:小:在线市场的算法博弈论问题
- 批准号:
2332922 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
Collaborative Research: FET: Small: Algorithmic Self-Assembly with Crisscross Slats
合作研究:FET:小型:十字交叉板条的算法自组装
- 批准号:
2329908 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
NeTS: Small: ML-Driven Online Traffic Analysis at Multi-Terabit Line Rates
NeTS:小型:ML 驱动的多太比特线路速率在线流量分析
- 批准号:
2331111 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Small: LEGAS: Learning Evolving Graphs At Scale
协作研究:SHF:小型:LEGAS:大规模学习演化图
- 批准号:
2331302 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Small: LEGAS: Learning Evolving Graphs At Scale
协作研究:SHF:小型:LEGAS:大规模学习演化图
- 批准号:
2331301 - 财政年份:2024
- 资助金额:
$ 18.58万 - 项目类别:
Standard Grant