DSNNs: learning transfer from deep neural networks to spiking neural networks

被引：0
|
作者：
Zhang L. [1 ,2 ,3 ]
Du Z. [1 ,2 ,3 ]
Li L. [4 ]
Chen Y. [1 ,2 ]
机构：
[1] State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing
[2] Institute of Computing Technology, Chinese Academy of Sciences, Beijing
[3] Cambricon Tech. Ltd, Beijing
[4] Institute of Software, Chinese Academy of Sciences, Beijing
来源：
High Technology Letters | 2020年 / 26卷 / 02期
基金：
中国国家自然科学基金;
关键词：
Convert method; Deep leaning; Spatially folded network; Spiking neural network (SNN);
D O I：
10.3772/j.issn.1006-6748.2020.02.002
中图分类号：
学科分类号：
摘要：
Deep neural networks (DNNs) have drawn great attention as they perform the state-of-the-art results on many tasks. Compared to DNNs, spiking neural networks (SNNs), which are considered as the new generation of neural networks, fail to achieve comparable performance especially on tasks with large problem sizes. Many previous work tried to close the gap between DNNs and SNNs but used small networks on simple tasks. This work proposes a simple but effective way to construct deep spiking neural networks (DSNNs) by transferring the learned ability of DNNs to SNNs. DSNNs achieve comparable accuracy on large networks and complex datasets. Copyright © by HIGH TECHNOLOGY LETTERS PRESS.
引用
收藏
页码：136 / 144
页数：8
相关论文
共 50 条
  • [41] Can Deep Neural Networks be Converted to Ultra Low-Latency Spiking Neural Networks?
    Datta, Gourav
    Beerel, Peter A.
    PROCEEDINGS OF THE 2022 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2022), 2022, : 718 - 723
  • [42] Detection of weather images by using spiking neural networks of deep learning models
    Togacar, Mesut
    Ergen, Burhan
    Comert, Zafer
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (11): : 6147 - 6159
  • [43] Deep Learning in Spiking Neural Networks for Brain-Inspired Artificial intelligence
    Kasabov, Nikola
    COMPUTER SYSTEMS AND TECHNOLOGIES (COMPSYSTECH'18), 2018, 1641 : 1 - 1
  • [44] Enabling On-Device Learning with Deep Spiking Neural Networks for Speech Recognition
    Soures, N. M.
    Kudithipudi, D.
    Jacobs-Gedrim, R. B.
    Agarwal, S.
    Marinella, M.
    SILICON COMPATIBLE MATERIALS, PROCESSES, AND TECHNOLOGIES FOR ADVANCED INTEGRATED CIRCUITS AND EMERGING APPLICATIONS 8, 2018, 85 (06): : 127 - 137
  • [45] Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
    Zhang, Wenrui
    Li, Peng
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [46] Deep Convolutional Spiking Neural Networks for Keyword Spotting
    Yilmaz, Emre
    Gevrek, Ozgur Bora
    Wu, Jibin
    Chen, Yuxiang
    Meng, Xuanbo
    Li, Haizhou
    INTERSPEECH 2020, 2020, : 2557 - 2561
  • [47] Backpropagation-Based Learning Techniques for Deep Spiking Neural Networks: A Survey
    Dampfhoffer, Manon
    Mesquida, Thomas
    Valentian, Alexandre
    Anghel, Lorena
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 35 (09) : 11906 - 11921
  • [48] Detection of weather images by using spiking neural networks of deep learning models
    Mesut Toğaçar
    Burhan Ergen
    Zafer Cömert
    Neural Computing and Applications, 2021, 33 : 6147 - 6159
  • [49] Neuromorphic deep spiking neural networks for seizure detection
    Yang, Yikai
    Eshraghian, Jason K.
    Truong, Nhan Duy
    Nikpour, Armin
    Kavehei, Omid
    NEUROMORPHIC COMPUTING AND ENGINEERING, 2023, 3 (01):
  • [50] Reducing the Spike Rate in Deep Spiking Neural Networks
    Fontanini, Riccardo
    Esseni, David
    Loghi, Mirko
    PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NEUROMORPHIC SYSTEMS 2022, ICONS 2022, 2022,
12345