基于模式分类器的信息映射：一项对比研究。
Information mapping with pattern classifiers: a comparative study.
机构信息
Psychology Department and Princeton, Neuroscience Institute, Princeton University, Princeton, NJ 08542, USA.
出版信息
Neuroimage. 2011 May 15;56(2):476-96. doi: 10.1016/j.neuroimage.2010.05.026. Epub 2010 May 17.
Abstract
Information mapping using pattern classifiers has become increasingly popular in recent years, although without a clear consensus on which classifier(s) ought to be used or how results should be tested. This paper addresses each of these questions, both analytically and through comparative analyses on five empirical datasets. We also describe how information maps in multiple class situations can provide information concerning the content of neural representations. Finally, we introduce a publically available software toolbox designed specifically for information mapping.
摘要
近年来，基于模式分类器的信息映射技术日益流行，尽管对于应该使用哪种（些）分类器以及如何测试结果，尚未达成明确共识。本文通过对五个实证数据集的分析和比较，分别对这些问题进行了探讨。我们还描述了在多类别情况下，信息图如何提供有关神经表示内容的信息。最后，我们引入了一个专门为信息映射设计的、可公开获取的软件工具箱。
相似文献
1
Information mapping with pattern classifiers: a comparative study.基于模式分类器的信息映射：一项对比研究。
Neuroimage. 2011 May 15;56(2):476-96. doi: 10.1016/j.neuroimage.2010.05.026. Epub 2010 May 17.
2
How to compute reliability estimates and display confidence and tolerance intervals for pattern classifiers using the Bootstrap and 3-way multidimensional scaling (DISTATIS).如何使用自助法和三向多维标度法（DISTATIS）计算模式分类器的可靠性估计值并显示置信区间和容忍区间。
Neuroimage. 2009 Mar 1;45(1):89-95. doi: 10.1016/j.neuroimage.2008.11.008. Epub 2008 Nov 24.
3
Unsupervised learning of brain states from fMRI data.基于功能磁共振成像（fMRI）数据的脑状态无监督学习。
Med Image Comput Comput Assist Interv. 2010;13(Pt 2):201-8. doi: 10.1007/978-3-642-15745-5_25.
4
Pattern classification of fMRI data: applications for analysis of spatially distributed cortical networks.功能磁共振成像（fMRI）数据的模式分类：用于分析空间分布的皮质网络的应用。
Neuroimage. 2014 Aug 1;96:117-32. doi: 10.1016/j.neuroimage.2014.03.074. Epub 2014 Apr 4.
5
Multiclass fMRI data decoding and visualization using supervised self-organizing maps.使用监督自组织映射进行多类 fMRI 数据解码和可视化。
Neuroimage. 2014 Aug 1;96:54-66. doi: 10.1016/j.neuroimage.2014.02.006. Epub 2014 Feb 12.
6
Extracting brain regions from rest fMRI with total-variation constrained dictionary learning.基于全变差约束字典学习从静息态功能磁共振成像中提取脑区
Med Image Comput Comput Assist Interv. 2013;16(Pt 2):607-15. doi: 10.1007/978-3-642-40763-5_75.
7
Reliability of dissimilarity measures for multi-voxel pattern analysis.用于多体素模式分析的差异度量的可靠性
Neuroimage. 2016 Aug 15;137:188-200. doi: 10.1016/j.neuroimage.2015.12.012. Epub 2015 Dec 18.
8
Information fusion in biomedical image analysis: combination of data vs. combination of interpretations.生物医学图像分析中的信息融合：数据组合与解释组合
Inf Process Med Imaging. 2005;19:150-61. doi: 10.1007/11505730_13.
9
Simultaneous registration and segmentation of anatomical structures from brain MRI.基于脑部磁共振成像的解剖结构同步配准与分割
Med Image Comput Comput Assist Interv. 2005;8(Pt 1):17-25. doi: 10.1007/11566465_3.
10
Unsupervised learning and mapping of active brain functional MRI signals based on hidden semi-Markov event sequence models.基于隐半马尔可夫事件序列模型的主动脑功能磁共振成像信号的无监督学习与映射
IEEE Trans Med Imaging. 2005 Feb;24(2):263-76. doi: 10.1109/tmi.2004.841225.
引用本文的文献
1
Decoding semantic sound categories in early visual cortex.早期视觉皮层中语义声音类别的解码
Cereb Cortex. 2025 Aug 1;35(8). doi: 10.1093/cercor/bhaf208.
2
Explainable artificial intelligence (xAI) in neuromarketing/consumer neuroscience: an fMRI study on brand perception.神经营销/消费者神经科学中的可解释人工智能（xAI）：一项关于品牌认知的功能磁共振成像研究
Front Hum Neurosci. 2024 Mar 22;18:1305164. doi: 10.3389/fnhum.2024.1305164. eCollection 2024.
3
Moral foundations elicit shared and dissociable cortical activation modulated by political ideology.道德基础引发了共享和可分离的皮质激活，这种激活受到政治意识形态的调节。
Nat Hum Behav. 2023 Dec;7(12):2182-2198. doi: 10.1038/s41562-023-01693-8. Epub 2023 Sep 7.
4
Identifying causal subsequent memory effects.识别因果性后续记忆效应。
Proc Natl Acad Sci U S A. 2023 Mar 28;120(13):e2120288120. doi: 10.1073/pnas.2120288120. Epub 2023 Mar 23.
5
Disentangling Object Category Representations Driven by Dynamic and Static Visual Input.解开由动态和静态视觉输入驱动的物体类别表示。
J Neurosci. 2023 Jan 25;43(4):621-634. doi: 10.1523/JNEUROSCI.0371-22.2022. Epub 2022 Dec 6.
6
Audiovisual Representations of Valence: a Cross-study Perspective.效价的视听表征：跨研究视角
Affect Sci. 2020 Nov 25;1(4):237-246. doi: 10.1007/s42761-020-00023-9. eCollection 2020 Dec.
7
The role of the anterior temporal cortex in action: evidence from fMRI multivariate searchlight analysis during real object grasping.额前颞叶皮质在动作中的作用：来自 fMRI 多元搜索光分析在真实物体抓握中的证据。
Sci Rep. 2022 Jun 5;12(1):9042. doi: 10.1038/s41598-022-12174-9.
8
Dynamical Network Models From EEG and MEG for Epilepsy Surgery-A Quantitative Approach.用于癫痫手术的基于脑电图和脑磁图的动态网络模型——一种定量方法。
Front Neurol. 2022 Mar 29;13:837893. doi: 10.3389/fneur.2022.837893. eCollection 2022.
9
Informative neural representations of unseen contents during higher-order processing in human brains and deep artificial networks.人类大脑和深度人工网络中高阶处理期间未观察到内容的信息神经表示。
Nat Hum Behav. 2022 May;6(5):720-731. doi: 10.1038/s41562-021-01274-7. Epub 2022 Feb 3.
10
Dynamic selective auditory attention detection using RNN and reinforcement learning.基于 RNN 和强化学习的动态选择性听觉注意力检测。
Sci Rep. 2021 Jul 29;11(1):15497. doi: 10.1038/s41598-021-94876-0.
本文引用的文献
1
Selective averaging of rapidly presented individual trials using fMRI.利用 fMRI 对快速呈现的单个试验进行选择性平均。
Hum Brain Mapp. 1997;5(5):329-40. doi: 10.1002/(SICI)1097-0193(1997)5:5<329::AID-HBM1>3.0.CO;2-5.
2
Recollection, familiarity, and cortical reinstatement: a multivoxel pattern analysis.回忆、熟悉感与皮层恢复：一种多体素模式分析
Neuron. 2009 Sep 10;63(5):697-708. doi: 10.1016/j.neuron.2009.08.011.
3
Circular analysis in systems neuroscience: the dangers of double dipping.系统神经科学中的循环分析：二次利用数据的风险。
Nat Neurosci. 2009 May;12(5):535-40. doi: 10.1038/nn.2303.
4
PyMVPA: A python toolbox for multivariate pattern analysis of fMRI data.PyMVPA：用于功能磁共振成像数据多变量模式分析的Python工具箱。
Neuroinformatics. 2009 Spring;7(1):37-53. doi: 10.1007/s12021-008-9041-y. Epub 2009 Jan 28.
5
Revealing representational content with pattern-information fMRI--an introductory guide.利用模式信息功能磁共振成像揭示表征内容——入门指南。
Soc Cogn Affect Neurosci. 2009 Mar;4(1):101-9. doi: 10.1093/scan/nsn044. Epub 2009 Jan 17.
6
Machine learning classifiers and fMRI: a tutorial overview.机器学习分类器与功能磁共振成像：教程概述
Neuroimage. 2009 Mar;45(1 Suppl):S199-209. doi: 10.1016/j.neuroimage.2008.11.007. Epub 2008 Nov 21.
7
Predicting human brain activity associated with the meanings of nouns.预测与名词含义相关的人类大脑活动。
Science. 2008 May 30;320(5880):1191-5. doi: 10.1126/science.1152876.
8
Brain reading using full brain support vector machines for object recognition: there is no "face" identification area.使用全脑支持向量机进行物体识别的脑阅读：不存在“面部”识别区域。
Neural Comput. 2008 Feb;20(2):486-503. doi: 10.1162/neco.2007.09-06-340.
9
Beyond mind-reading: multi-voxel pattern analysis of fMRI data.超越读心术：功能磁共振成像数据的多体素模式分析
Trends Cogn Sci. 2006 Sep;10(9):424-30. doi: 10.1016/j.tics.2006.07.005. Epub 2006 Aug 8.
10
Decoding mental states from brain activity in humans.从人类大脑活动中解码心理状态。
Nat Rev Neurosci. 2006 Jul;7(7):523-34. doi: 10.1038/nrn1931.
Zotero 插件