Restricted Boltzmann machines for neuroimaging: An application in identifying intrinsic networks

被引:110
|
作者
Hjelm, R. Devon [1 ,2 ]
Calhoun, Vince D. [1 ,2 ]
Salakhutdinov, Ruslan [3 ]
Allen, Elena A. [1 ,5 ]
Adali, Tulay [4 ]
Plis, Sergey M. [1 ]
机构
[1] Mind Res Network, Albuquerque, NM 87106 USA
[2] Univ New Mexico, Dept Comp Sci, Albuquerque, NM 87131 USA
[3] Univ Toronto, Dept Comp Sci, Toronto, ON M5S 2J7, Canada
[4] Univ Maryland Baltimore Cty, Baltimore, MD 21250 USA
[5] Univ Bergen, Dept Biol & Med Psychol, N-5009 Bergen, Norway
关键词
RBM; ICA; DBN; Intrinsic networks; fMRI; CONNECTIVITY; CORTEX;
D O I
10.1016/j.neuroimage.2014.03.048
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Matrix factorization models are the current dominant approach for resolving meaningful data-driven features in neuroimaging data. Among them, independent component analysis (ICA) is arguably the most widely used for identifying functional networks, and its success has led to a number of versatile extensions to group and multi-modal data. However there are indications that ICA may have reached a limit in flexibility and representational capacity, as the majority of such extensions are case-driven, custom-made solutions that are still contained within the class of mixture models. In this work, we seek out a principled and naturally extensible approach and consider a probabilistic model known as a restricted Boltzmann machine (RBM). An RBM separates linear factors from functional brain imaging data by fitting a probability distribution model to the data. Importantly, the solution can be used as a building block for more complex (deep) models, making it naturally suitable for hierarchical and multimodal extensions that are not easily captured when using linear factorizations alone. We investigate the capability of RBMs to identify intrinsic networks and compare its performance to that of well-known linear mixture models, in particular ICA. Using synthetic and real task fMRI data, we show that RBMs can be used to identify networks and their temporal activations with accuracy that is equal or greater than that of factorization models. The demonstrated effectiveness of RBMs supports its use as a building block for deeper models, a significant prospect for future neuroimaging research. (C) 2014 Elsevier Inc. All rights reserved.
引用
收藏
页码:245 / 260
页数:16
相关论文
共 50 条
  • [1] Identifying product order with restricted Boltzmann machines
    Rao, Wen-Jia
    Li, Zhenyu
    Zhu, Qiong
    Luo, Mingxing
    Wan, Xin
    [J]. PHYSICAL REVIEW B, 2018, 97 (09)
  • [2] Identifying data streams anomalies by evolving spiking restricted Boltzmann machines
    Xing, Lining
    Demertzis, Konstantinos
    Yang, Jinghui
    [J]. NEURAL COMPUTING & APPLICATIONS, 2020, 32 (11): : 6699 - 6713
  • [3] Identifying data streams anomalies by evolving spiking restricted Boltzmann machines
    Lining Xing
    Konstantinos Demertzis
    Jinghui Yang
    [J]. Neural Computing and Applications, 2020, 32 : 6699 - 6713
  • [4] Neuromorphic Adaptations of Restricted Boltzmann Machines and Deep Belief Networks
    Pedroni, Bruno U.
    Das, Srinjoy
    Neftci, Emre
    Kreutz-Delgado, Kenneth
    Cauwenberghs, Gert
    [J]. 2013 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2013,
  • [5] Representational power of restricted Boltzmann machines and deep belief networks
    Le Roux, Nicolas
    Bengio, Yoshua
    [J]. NEURAL COMPUTATION, 2008, 20 (06) : 1631 - 1649
  • [6] Restricted Boltzmann Machines and Deep Belief Networks on Sunway Cluster
    Song, Kaida
    Liu, Yi
    Wang, Rui
    Zhao, Meiting
    Hao, Ziyu
    Qian, Depei
    [J]. PROCEEDINGS OF 2016 IEEE 18TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS; IEEE 14TH INTERNATIONAL CONFERENCE ON SMART CITY; IEEE 2ND INTERNATIONAL CONFERENCE ON DATA SCIENCE AND SYSTEMS (HPCC/SMARTCITY/DSS), 2016, : 245 - 252
  • [7] Analysis on Noisy Boltzmann Machines and Noisy Restricted Boltzmann Machines
    Lu, Wenhao
    Leung, Chi-Sing
    Sum, John
    [J]. IEEE ACCESS, 2021, 9 : 112955 - 112965
  • [8] An Overview of Restricted Boltzmann Machines
    Upadhya, Vidyadhar
    Sastry, P. S.
    [J]. JOURNAL OF THE INDIAN INSTITUTE OF SCIENCE, 2019, 99 (02) : 225 - 236
  • [9] Discrete Restricted Boltzmann Machines
    Montufar, Guido
    Morton, Jason
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2015, 16 : 653 - 672
  • [10] Restricted Boltzmann Machines: A Review
    Zhang, Jian
    Ding, Shi-Fei
    Zhang, Nan
    Du, Peng
    Du, Wei
    Yu, Wen-Jia
    [J]. Ruan Jian Xue Bao/Journal of Software, 2019, 30 (07): : 2073 - 2090