探索 fMRI RDM:通过神经生物学数据增强模型稳健性

IF 2.4 Q3 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
W. Pickard, Kelsey Sikes, Huma Jamil, Nicholas Chaffee, Nathaniel Blanchard, Michael Kirby, Christopher Peterson
{"title":"探索 fMRI RDM:通过神经生物学数据增强模型稳健性","authors":"W. Pickard, Kelsey Sikes, Huma Jamil, Nicholas Chaffee, Nathaniel Blanchard, Michael Kirby, Christopher Peterson","doi":"10.3389/fcomp.2023.1275026","DOIUrl":null,"url":null,"abstract":"Artificial neural networks (ANNs) are sensitive to perturbations and adversarial attacks. One hypothesized solution to adversarial robustness is to align manifolds in the embedded space of neural networks with biologically grounded manifolds. Recent state-of-the-art works that emphasize learning robust neural representations, rather than optimizing for a specific target task like classification, support the idea that researchers should investigate this hypothesis. While works have shown that fine-tuning ANNs to coincide with biological vision does increase robustness to both perturbations and adversarial attacks, these works have relied on proprietary datasets—the lack of publicly available biological benchmarks makes it difficult to evaluate the efficacy of these claims. Here, we deliver a curated dataset consisting of biological representations of images taken from two commonly used computer vision datasets, ImageNet and COCO, that can be easily integrated into model training and evaluation. Specifically, we take a large functional magnetic resonance imaging (fMRI) dataset (BOLD5000), preprocess it into representational dissimilarity matrices (RDMs), and establish an infrastructure that anyone can use to train models with biologically grounded representations. Using this infrastructure, we investigate the representations of several popular neural networks and find that as networks have been optimized for tasks, their correspondence with biological fidelity has decreased. Additionally, we use a previously unexplored graph-based technique, Fiedler partitioning, to showcase the viability of the biological data, and the potential to extend these analyses by extending RDMs into Laplacian matrices. Overall, our findings demonstrate the potential of utilizing our new biological benchmark to effectively enhance the robustness of models.","PeriodicalId":52823,"journal":{"name":"Frontiers in Computer Science","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Exploring fMRI RDMs: enhancing model robustness through neurobiological data\",\"authors\":\"W. Pickard, Kelsey Sikes, Huma Jamil, Nicholas Chaffee, Nathaniel Blanchard, Michael Kirby, Christopher Peterson\",\"doi\":\"10.3389/fcomp.2023.1275026\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Artificial neural networks (ANNs) are sensitive to perturbations and adversarial attacks. One hypothesized solution to adversarial robustness is to align manifolds in the embedded space of neural networks with biologically grounded manifolds. Recent state-of-the-art works that emphasize learning robust neural representations, rather than optimizing for a specific target task like classification, support the idea that researchers should investigate this hypothesis. While works have shown that fine-tuning ANNs to coincide with biological vision does increase robustness to both perturbations and adversarial attacks, these works have relied on proprietary datasets—the lack of publicly available biological benchmarks makes it difficult to evaluate the efficacy of these claims. Here, we deliver a curated dataset consisting of biological representations of images taken from two commonly used computer vision datasets, ImageNet and COCO, that can be easily integrated into model training and evaluation. Specifically, we take a large functional magnetic resonance imaging (fMRI) dataset (BOLD5000), preprocess it into representational dissimilarity matrices (RDMs), and establish an infrastructure that anyone can use to train models with biologically grounded representations. Using this infrastructure, we investigate the representations of several popular neural networks and find that as networks have been optimized for tasks, their correspondence with biological fidelity has decreased. Additionally, we use a previously unexplored graph-based technique, Fiedler partitioning, to showcase the viability of the biological data, and the potential to extend these analyses by extending RDMs into Laplacian matrices. Overall, our findings demonstrate the potential of utilizing our new biological benchmark to effectively enhance the robustness of models.\",\"PeriodicalId\":52823,\"journal\":{\"name\":\"Frontiers in Computer Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2023-12-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Computer Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/fcomp.2023.1275026\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Computer Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fcomp.2023.1275026","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

摘要

人工神经网络(ANN)对扰动和对抗性攻击非常敏感。对抗性鲁棒性的一个假设解决方案是将神经网络嵌入空间中的流形与生物流形相一致。最近的先进研究强调学习鲁棒性神经表征,而不是针对特定的目标任务(如分类)进行优化,这支持了研究人员应研究这一假设的想法。虽然有研究表明,微调人工神经网络使其与生物视觉相吻合确实能提高对扰动和对抗性攻击的鲁棒性,但这些研究都依赖于专有数据集--由于缺乏公开可用的生物基准,因此很难评估这些说法的有效性。在这里,我们提供了一个精心策划的数据集,该数据集由两个常用计算机视觉数据集(ImageNet 和 COCO)中的图像生物表示组成,可以轻松集成到模型训练和评估中。具体来说,我们采用了一个大型功能性磁共振成像(fMRI)数据集(BOLD5000),将其预处理为表征异质性矩阵(RDM),并建立了一个任何人都可以使用的基础设施,利用生物表征训练模型。利用这一基础架构,我们研究了几种流行神经网络的表征,发现随着网络针对任务的优化,它们与生物保真度的对应关系有所下降。此外,我们还使用了一种以前未曾探索过的基于图的技术--费德勒分区,以展示生物数据的可行性,以及通过将 RDM 扩展到拉普拉卡矩阵来扩展这些分析的潜力。总之,我们的研究结果证明了利用我们的新生物基准有效增强模型稳健性的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Exploring fMRI RDMs: enhancing model robustness through neurobiological data
Artificial neural networks (ANNs) are sensitive to perturbations and adversarial attacks. One hypothesized solution to adversarial robustness is to align manifolds in the embedded space of neural networks with biologically grounded manifolds. Recent state-of-the-art works that emphasize learning robust neural representations, rather than optimizing for a specific target task like classification, support the idea that researchers should investigate this hypothesis. While works have shown that fine-tuning ANNs to coincide with biological vision does increase robustness to both perturbations and adversarial attacks, these works have relied on proprietary datasets—the lack of publicly available biological benchmarks makes it difficult to evaluate the efficacy of these claims. Here, we deliver a curated dataset consisting of biological representations of images taken from two commonly used computer vision datasets, ImageNet and COCO, that can be easily integrated into model training and evaluation. Specifically, we take a large functional magnetic resonance imaging (fMRI) dataset (BOLD5000), preprocess it into representational dissimilarity matrices (RDMs), and establish an infrastructure that anyone can use to train models with biologically grounded representations. Using this infrastructure, we investigate the representations of several popular neural networks and find that as networks have been optimized for tasks, their correspondence with biological fidelity has decreased. Additionally, we use a previously unexplored graph-based technique, Fiedler partitioning, to showcase the viability of the biological data, and the potential to extend these analyses by extending RDMs into Laplacian matrices. Overall, our findings demonstrate the potential of utilizing our new biological benchmark to effectively enhance the robustness of models.
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
Frontiers in Computer Science
Frontiers in Computer Science COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS-
CiteScore
4.30
自引率
0.00%
发文量
152
审稿时长
13 weeks
×
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