Efficient design of complex-valued neural networks with application to the classification of transient acoustic signals

被引:1
作者
Paul, Vlad S. [1 ]
Nelson, Philip A. [1 ]
机构
[1] Univ Southampton, Inst Sound & Vibrat Res, Southampton SO17 1BJ, Hants, England
基金
英国工程与自然科学研究理事会;
关键词
ALGORITHM;
D O I
10.1121/10.0028230
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
A paper by the current authors Paul and Nelson [JASA Express Lett. 3(9), 094802 (2023)] showed how the singular value decomposition (SVD) of the matrix of real weights in a neural network could be used to prune the network during training. The paper presented here shows that a similar approach can be used to reduce the training time and increase the implementation efficiency of complex-valued neural networks. Such networks have potential advantages compared to their real-valued counterparts, especially when the complex representation of the data is important, which is the often case in acoustic signal processing. In comparing the performance of networks having both real and complex elements, it is demonstrated that there are some advantages to the use of complex networks in the cases considered. The paper includes a derivation of the backpropagation algorithm, in matrix form, for training a complex-valued multilayer perceptron with an arbitrary number of layers. The matrix-based analysis enables the application of the SVD to the complex weight matrices in the network. The SVD-based pruning technique is applied to the problem of the classification of transient acoustic signals. It is shown how training times can be reduced, and implementation efficiency increased, while ensuring that such signals can be classified with remarkable accuracy.
引用
收藏
页码:1099 / 1110
页数:12
相关论文
共 45 条
  • [41] The formal theory of functions of many complex variables
    Wirtinger, W
    [J]. MATHEMATISCHE ANNALEN, 1927, 97 : 357 - +
  • [42] Xue J, 2013, INTERSPEECH, P2364
  • [43] Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
    Yang, Huanrui
    Tang, Minxue
    Wen, Wei
    Yan, Feng
    Hu, Daniel
    Li, Ang
    Li, Hai
    Chen, Yiran
    [J]. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, : 2899 - 2908
  • [44] Is a Complex-Valued Stepsize Advantageous in Complex-Valued Gradient Learning Algorithms?
    Zhang, Huisheng
    Mandic, Danilo P.
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2016, 27 (12) : 2730 - 2735
  • [45] Convergence analysis of fully complex backpropagation algorithm based on Wirtinger calculus
    Zhang, Huisheng
    Liu, Xiaodong
    Xu, Dongpo
    Zhang, Ying
    [J]. COGNITIVE NEURODYNAMICS, 2014, 8 (03) : 261 - 266