A large-scale evaluation framework for EEG deep learning architectures

被引:8
|
作者
Heilmeyer, Felix A. [1 ]
Schirrmeister, Robin T. [1 ]
Fiederer, Lukas D. J. [1 ]
Voelker, Martin [1 ]
Behncke, Joos [1 ]
Ball, Tonio [1 ]
机构
[1] Univ Med Ctr Freiburg, Translat Neurotechnol Lab, Freiburg, Germany
关键词
EEG; BCI; Deep Learning; Convolutional Neural Networks; Braindecode; EEGNet; FBCSP; Performance Comparison;
D O I
10.1109/SMC.2018.00185
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
EEG is the most common signal source for noninvasive BCI applications. For such applications, the EEG signal needs to be decoded and translated into appropriate actions. A recently emerging EEG decoding approach is deep learning with Convolutional or Recurrent Neural Networks (CNNs, RNNs) with many different architectures already published. Here we present a novel framework for the large-scale evaluation of different deep-learning architectures on different EEG datasets. This framework comprises (i) a collection of EEG datasets currently including 100 examples (recording sessions) from six different classification problems, (ii) a collection of different EEG decoding algorithms, and (iii) a wrapper linking the decoders to the data as well as handling structured documentation of all settings and (hyper-) parameters and statistics, designed to ensure transparency and reproducibility. As an applications example we used our framework by comparing three publicly available CNN architectures: the Braindecode Deep4 ConvNet, Braindecode Shallow ConvNet, and two versions of EEGNet. We also show how our framework can be used to study similarities and differences in the performance of different decoding methods across tasks. We argue that the deep learning EEG framework as described here could help to tap the full potential of deep learning for BCI applications.
引用
收藏
页码:1039 / 1045
页数:7
相关论文
共 50 条
  • [1] Distributed Training Large-Scale Deep Architectures
    Zou, Shang-Xuan
    Chen, Chun-Yen
    Wu, Jui-Lin
    Chou, Chun-Nan
    Tsao, Chia-Chin
    Tung, Kuan-Chieh
    Lin, Ting-Wei
    Sung, Cheng-Lung
    Chang, Edward Y.
    ADVANCED DATA MINING AND APPLICATIONS, ADMA 2017, 2017, 10604 : 18 - 32
  • [2] DDHH: A Decentralized Deep Learning Framework for Large-scale Heterogeneous Networks
    Imran, Mubashir
    Yin, Hongzhi
    Chen, Tong
    Huang, Zi
    Zhang, Xiangliang
    Zheng, Kai
    2021 IEEE 37TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2021), 2021, : 2033 - 2038
  • [3] Hybrid Electrical/Optical Switch Architectures for Training Distributed Deep Learning in Large-Scale
    Thao-Nguyen Truong
    Takano, Ryousei
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2021, E104D (08) : 1332 - 1339
  • [4] Large-scale Deep Learning at Baidu
    Yu, Kai
    PROCEEDINGS OF THE 22ND ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM'13), 2013, : 2211 - 2211
  • [5] Implementation of a Large-Scale Image Curation Workflow Using Deep Learning Framework
    Domalpally, Amitha
    Slater, Robert
    Barrett, Nancy
    Voland, Rick
    Balaji, Rohit
    Heathcote, Jennifer
    Channa, Roomasa
    Blodi, Barbara
    OPHTHALMOLOGY SCIENCE, 2022, 2 (04):
  • [6] swFLOW: A large-scale distributed framework for deep learning on Sunway TaihuLight supercomputer
    Li, Mingfan
    Lin, Han
    Chen, Junshi
    Diaz, Jose Monsalve
    Xiao, Qian
    Lin, Rongfen
    Wang, Fei
    Gao, Guang R.
    An, Hong
    INFORMATION SCIENCES, 2021, 570 (570) : 831 - 847
  • [7] Large-scale transport simulation by deep learning
    Jie Pan
    Nature Computational Science, 2021, 1 : 306 - 306
  • [8] Tractable large-scale deep reinforcement learning
    Sarang, Nima
    Poullis, Charalambos
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2023, 232
  • [9] Large-scale transport simulation by deep learning
    Pan, Jie
    NATURE COMPUTATIONAL SCIENCE, 2021, 1 (05): : 306 - 306
  • [10] The three pillars of large-scale deep learning
    Hoefler, Torsten
    2021 IEEE INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2021, : 908 - 908