Reproducibility in Matrix and Tensor Decompositions: Focus on Model Match, Interpretability, and Uniqueness.
作者信息
Adali Tülay, Kantar Furkan, Akhonda M A B Siddique, Strother Stephen, Calhoun Vince D, Acar Evrim
机构信息
Department of CSEE, University of Maryland, Baltimore County, Baltimore, MD, USA.
Rotman Research Center, Baycrest, and Department of Medical Biophysics, University of Toronto, ON, Canada.
出版信息
IEEE Signal Process Mag. 2022 Jul;39(4):8-24. doi: 10.1109/msp.2022.3163870. Epub 2022 Jun 28.
Abstract
摘要
相似文献
1
Reproducibility in Matrix and Tensor Decompositions: Focus on Model Match, Interpretability, and Uniqueness.矩阵和张量分解中的可重复性：关注模型匹配、可解释性和唯一性。
IEEE Signal Process Mag. 2022 Jul;39(4):8-24. doi: 10.1109/msp.2022.3163870. Epub 2022 Jun 28.
2
Efficient Nonnegative Tucker Decompositions: Algorithms and Uniqueness.高效非负 Tucker 分解：算法与唯一性。
IEEE Trans Image Process. 2015 Dec;24(12):4990-5003. doi: 10.1109/TIP.2015.2478396. Epub 2015 Sep 14.
3
Tensor decompositions for the analysis of atomic resolution electron energy loss spectra.用于分析原子分辨率电子能量损失谱的张量分解
Ultramicroscopy. 2017 Apr;175:36-45. doi: 10.1016/j.ultramic.2016.12.025. Epub 2017 Jan 11.
4
Sufficient conditions for uniqueness in Candecomp/Parafac and Indscal with random component matrices.在具有随机成分矩阵的Candecomp/Parafac和Indscal中唯一性的充分条件。
Psychometrika. 2006 Jun;71(2):219-229. doi: 10.1007/11336-006-1278-2. Epub 2017 Feb 11.
5
Tensor Networks for Latent Variable Analysis: Novel Algorithms for Tensor Train Approximation.用于潜在变量分析的张量网络：张量列车逼近的新算法
IEEE Trans Neural Netw Learn Syst. 2020 Nov;31(11):4622-4636. doi: 10.1109/TNNLS.2019.2956926. Epub 2020 Oct 30.
6
Monitoring of Brain Hemodynamics Coupling in Neonates using Updated Tensor Decompositions.使用更新的张量分解监测新生儿脑血流动力学耦合
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:660-663. doi: 10.1109/EMBC.2019.8857846.
7
CUR matrix decompositions for improved data analysis.用于改进数据分析的CUR矩阵分解。
Proc Natl Acad Sci U S A. 2009 Jan 20;106(3):697-702. doi: 10.1073/pnas.0803205106. Epub 2009 Jan 12.
8
Algorithms for sparse nonnegative Tucker decompositions.稀疏非负塔克分解算法。
Neural Comput. 2008 Aug;20(8):2112-31. doi: 10.1162/neco.2008.11-06-407.
9
DIADECOMP: A new approach to analyze decompositions from projection spectroscopy.DIADECOMP：一种分析投影光谱分解的新方法。
J Magn Reson. 2016 Dec;273:1-8. doi: 10.1016/j.jmr.2016.10.002. Epub 2016 Oct 3.
10
Near-lossless multichannel EEG compression based on matrix and tensor decompositions.基于矩阵和张量分解的近无损多通道 EEG 压缩。
IEEE J Biomed Health Inform. 2013 May;17(3):708-14. doi: 10.1109/titb.2012.2230012.
引用本文的文献
1
Exploring synergies: Advancing neuroscience with machine learning.探索协同效应：借助机器学习推动神经科学发展。
Signal Processing. 2026 Jan;238. doi: 10.1016/j.sigpro.2025.110116. Epub 2025 Jun 2.
2
A telescopic independent component analysis on functional magnetic resonance imaging dataset.基于功能磁共振成像数据集的伸缩独立成分分析。
Netw Neurosci. 2025 Mar 3;9(1):61-76. doi: 10.1162/netn_a_00421. eCollection 2025.
3
Longitudinal Metabolomics Data Analysis Informed by Mechanistic Models.基于机理模型的纵向代谢组学数据分析
Metabolites. 2024 Dec 24;15(1):2. doi: 10.3390/metabo15010002.
4
A Telescopic Independent Component Analysis on Functional Magnetic Resonance Imaging Data Set.基于功能磁共振成像数据集的伸缩式独立成分分析
bioRxiv. 2024 Sep 27:2024.02.19.581086. doi: 10.1101/2024.02.19.581086.
5
Revealing static and dynamic biomarkers from postprandial metabolomics data through coupled matrix and tensor factorizations.通过耦合矩阵和张量分解揭示餐后代谢组学数据中的静态和动态生物标志物。
Metabolomics. 2024 Jul 27;20(4):86. doi: 10.1007/s11306-024-02128-9.
6
Constrained Independent Vector Analysis With Reference for Multi-Subject fMRI Analysis.用于多受试者功能磁共振成像分析的带参考的约束独立向量分析
IEEE Trans Biomed Eng. 2024 Dec;71(12):3531-3542. doi: 10.1109/TBME.2024.3432273. Epub 2024 Nov 21.
7
Characterizing human postprandial metabolic response using multiway data analysis.采用多向数据分析方法描述人体餐后代谢反应。
Metabolomics. 2024 May 9;20(3):50. doi: 10.1007/s11306-024-02109-y.
8
Analyzing postprandial metabolomics data using multiway models: a simulation study.运用多向模型分析餐后代谢组学数据：一项模拟研究。
BMC Bioinformatics. 2024 Mar 4;25(1):94. doi: 10.1186/s12859-024-05686-w.
9
A Scalable Approach to Independent Vector Analysis by Shared Subspace Separation for Multi-Subject fMRI Analysis.基于共享子空间分离的多体 fMRI 分析的独立向量分析可扩展方法。
Sensors (Basel). 2023 Jun 5;23(11):5333. doi: 10.3390/s23115333.
10
An Indoor Fall Monitoring System: Robust, Multistatic Radar Sensing and Explainable, Feature-Resonated Deep Neural Network.一种室内跌倒监测系统：稳健的多静态雷达传感与可解释的特征共振深度神经网络
IEEE J Biomed Health Inform. 2023 Apr;27(4):1891-1902. doi: 10.1109/JBHI.2023.3237077. Epub 2023 Apr 4.
本文引用的文献
1
2
NeuroMark: An automated and adaptive ICA based pipeline to identify reproducible fMRI markers of brain disorders.NeuroMark：一种基于自动和自适应 ICA 的流水线，用于识别可重复的 fMRI 脑疾病标志物。
Neuroimage Clin. 2020;28:102375. doi: 10.1016/j.nicl.2020.102375. Epub 2020 Aug 11.
3
Independent vector analysis for common subspace analysis: Application to multi-subject fMRI data yields meaningful subgroups of schizophrenia.用于公共子空间分析的独立向量分析：应用于多受试者功能磁共振成像数据可得出有意义的精神分裂症亚组。
Neuroimage. 2020 Aug 1;216:116872. doi: 10.1016/j.neuroimage.2020.116872. Epub 2020 Apr 28.
4
ICA and IVA for Data Fusion: An Overview and a New Approach Based on Disjoint Subspaces.用于数据融合的独立成分分析和独立向量分析：综述与基于不相交子空间的新方法
IEEE Sens Lett. 2019 Jan;3(1). doi: 10.1109/LSENS.2018.2884775. Epub 2018 Dec 3.
5
Unraveling Diagnostic Biomarkers of Schizophrenia Through Structure-Revealing Fusion of Multi-Modal Neuroimaging Data.通过多模态神经影像数据的结构揭示融合来解析精神分裂症的诊断生物标志物
Front Neurosci. 2019 May 3;13:416. doi: 10.3389/fnins.2019.00416. eCollection 2019.
6
Temporal phenotyping of medically complex children via PARAFAC2 tensor factorization.通过 PARAFAC2 张量分解对医学上复杂的儿童进行时间表型分析。
J Biomed Inform. 2019 May;93:103125. doi: 10.1016/j.jbi.2019.103125. Epub 2019 Feb 8.
7
The Molecular Fingerprint of Fluorescent Natural Organic Matter Offers Insight into Biogeochemical Sources and Diagenetic State.荧光天然有机物质的分子指纹揭示了生物地球化学来源和成岩状态。
Anal Chem. 2018 Dec 18;90(24):14188-14197. doi: 10.1021/acs.analchem.8b02863. Epub 2018 Dec 3.
8
The role of diversity in data-driven analysis of multi-subject fMRI data: Comparison of approaches based on independence and sparsity using global performance metrics.多主体 fMRI 数据驱动分析中多样性的作用：基于独立性和稀疏性的方法的比较，使用全局性能指标。
Hum Brain Mapp. 2019 Feb 1;40(2):489-504. doi: 10.1002/hbm.24389. Epub 2018 Sep 21.
9
Unsupervised Discovery of Demixed, Low-Dimensional Neural Dynamics across Multiple Timescales through Tensor Component Analysis.通过张量成分分析，在多个时间尺度上对混合的、低维神经动力学进行无监督发现。
Neuron. 2018 Jun 27;98(6):1099-1115.e8. doi: 10.1016/j.neuron.2018.05.015. Epub 2018 Jun 7.
10
Multimodal Neuroimaging in Schizophrenia: Description and Dissemination.精神分裂症的多模态神经影像学：描述与传播。
Neuroinformatics. 2017 Oct;15(4):343-364. doi: 10.1007/s12021-017-9338-9.
Zotero 插件