An Unsupervised Spiking Deep Neural Network for Object Recognition

被引:2
|
作者
Song, Zeyang [1 ]
Wu, Xi [1 ]
Yuan, Mengwen [1 ]
Tang, Huajin [1 ]
机构
[1] Sichuan Univ, Coll Comp Sci, Neuromorph Comp Res Ctr, Chengdu 610065, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
HMAX; Spiking Deep Neural Network; STDP; Deep learning; Object recognition; MODEL;
D O I
10.1007/978-3-030-22808-8_36
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose an unsupervised HMAX-based Spiking Deep Neural Network (HMAX-SDNN) for object recognition. HMAX is a biologically plausible model based on the hierarchical activity of object recognition in visual cortex. In HMAX-SDNN, input layer with HMAX structure is followed by a stacked convolution-pooling structure, in which convolutional layers are hierarchically trained with STDP. After that, a linear SVM is used for classification. Then, we demonstrate that the firing threshold has positive correlation with receptive fields size in convolutional layers, and optimize HMAX-SDNN with this conclusion. With the optimized structure, we validate HMAX-SDNN on Caltech dataset, and HMAX-SDNN outperforms other SNNs by reaching 99.2% recognition accuracy. Furthermore, the experiments show that HMAX-SDNN is robust to different kinds of objects.
引用
收藏
页码:361 / 370
页数:10
相关论文
共 50 条
  • [1] An ensemble unsupervised spiking neural network for objective recognition
    Fu, Qiang
    Dong, Hongbin
    [J]. NEUROCOMPUTING, 2021, 419 : 47 - 58
  • [2] Object shape recognition using tactile sensor arrays by a spiking neural network with unsupervised learning
    Kim, Jaehun
    Kim, Sung-Phil
    Kim, Jungjun
    Hwang, Heeseon
    Kim, Jaehyun
    Park, Doowon
    Jeong, Unyong
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 178 - 183
  • [3] Spiking VGG7: Deep Convolutional Spiking Neural Network with Direct Training for Object Recognition
    Xiang, Shuiying
    Jiang, Shuqing
    Liu, Xiaosong
    Zhang, Tao
    Yu, Licun
    [J]. ELECTRONICS, 2022, 11 (13)
  • [4] Object and Character Recognition Using Spiking Neural Network
    Bawane, Priyanka
    Gadariye, Snehali
    Chaturvedi, S.
    Khurshid, A. A.
    [J]. MATERIALS TODAY-PROCEEDINGS, 2018, 5 (01) : 360 - 366
  • [5] Spiking SiamFC++: deep spiking neural network for object tracking
    Shuiying Xiang
    Tao Zhang
    Shuqing Jiang
    Yanan Han
    Yahui Zhang
    Xingxing Guo
    Licun Yu
    Yuechun Shi
    Yue Hao
    [J]. Nonlinear Dynamics, 2024, 112 : 8417 - 8429
  • [6] Finger Vein Recognition Based on Unsupervised Spiking Neural Network
    Yang, Li
    Xu, Xiang
    Yao, Qiong
    [J]. BIOMETRIC RECOGNITION, CCBR 2023, 2023, 14463 : 55 - 64
  • [7] Deep Spiking Neural Networks With Binary Weights for Object Recognition
    Wang, Yixuan
    Xu, Yang
    Yan, Rui
    Tang, Huajin
    [J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2021, 13 (03) : 514 - 523
  • [8] Unsupervised Regenerative Learning of Hierarchical Features in Spiking Deep Networks for Object Recognition
    Panda, Priyadarshini
    Roy, Kaushik
    [J]. 2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 299 - 306
  • [9] Spiking SiamFC plus plus : deep spiking neural network for object tracking
    Xiang, Shuiying
    Zhang, Tao
    Jiang, Shuqing
    Han, Yanan
    Zhang, Yahui
    Guo, Xingxing
    Yu, Licun
    Shi, Yuechun
    Hao, Yue
    [J]. NONLINEAR DYNAMICS, 2024, 112 (10) : 8417 - 8429
  • [10] A Spiking Neural Network for Tactile Form Based Object Recognition
    Ratnasingam, Sivalogeswaran
    McGinnity, T. M.
    [J]. 2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2011, : 880 - 885