Estimating the number of Hidden Nodes of the Single-hidden-layer Feedforward Neural Networks

被引：9
|
作者：
Cai, Guang-Wei [1 ]
Fang, Zhi [1 ]
Chen, Yue-Feng [2 ]
机构：
[1] Beijing Inst Comp Technol & Applicat, Beijing, Peoples R China
[2] 63963 Unit PLA, Beijing, Peoples R China
来源：
2019 15TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS 2019) | 2019年
关键词：
Single-hidden-layer feedforward neural network; hidden nodes; singular value decomposition; data normalization;
D O I：
10.1109/CIS.2019.00044
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In order to solve the problem that there is no effective means to find the optimal number of hidden nodes of single-hidden-layer feedforward neural network, in this paper, a method will be introduced to solve it effectively by using singular value decomposition. First, the training data need to be normalized strictly by attribute-based data normalization and sample-based data normalization. Then, the normalized data is decomposed based on the singular value decomposition, and the number of hidden nodes is determined according to main eigenvalues. The experimental results of MNIST data set and APS data set show that the feedforward neural network can attain satisfactory performance in the classification task.
引用
收藏
页码：172 / 176
页数：5
相关论文
共 50 条
  • [41] Adaptive output feedback control of uncertain nonlinear systems using single-hidden-layer neural networks
    Hovakimyan, N
    Nardi, F
    Calise, A
    Kim, N
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (06): : 1420 - 1431
  • [42] Iterative algorithm computational spectrometer based on a single-hidden-layer neural network
    Zheng, Yuanhao
    Liao, Haojie
    Yang, Lin
    Chen, Yao
    [J]. OPTICS EXPRESS, 2024, 32 (13): : 23316 - 23332
  • [43] Generating random weights and biases in feedforward neural networks with random hidden nodes
    Dudek, Grzegorz
    [J]. INFORMATION SCIENCES, 2019, 481 : 33 - 56
  • [44] Regularized online sequential learning algorithm for single-hidden layer feedforward neural networks
    Hieu Trung Huynh
    Won, Yonggwan
    [J]. PATTERN RECOGNITION LETTERS, 2011, 32 (14) : 1930 - 1935
  • [45] A new robust training algorithm for a class of single-hidden layer feedforward neural networks
    Man, Zhihong
    Lee, Kevin
    Wang, Dianhui
    Cao, Zhenwei
    Miao, Chunyan
    [J]. NEUROCOMPUTING, 2011, 74 (16) : 2491 - 2501
  • [46] On the comparison of random and Hebbian weights for the training of single-hidden layer feedforward neural networks
    Samiee, Kaveh
    Iosifidis, Alexandros
    Gabbouj, Moncef
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2017, 83 : 177 - 186
  • [47] On the solution of the parity problem by a single hidden layer feedforward neural network
    Dept. of Info. Syst. and Comp. Sci., National University of Singapore, Kent Ridge, Singapore 119260, Singapore
    [J]. NEUROCOMPUTING, 3 (225-235):
  • [48] On the solution of the parity problem by a single hidden layer feedforward neural network
    Setiono, R
    [J]. NEUROCOMPUTING, 1997, 16 (03) : 225 - 235
  • [49] Generalized Single-Hidden Layer Feedforward Networks for Regression Problems
    Wang, Ning
    Er, Meng Joo
    Han, Min
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (06) : 1161 - 1176
  • [50] Optimal hidden structure for feedforward neural networks
    Bachiller, P.
    Perez, R. M.
    Martinez, P.
    Aguilar, P. L.
    Diaz, P.
    [J]. COMPUTATIONAL INTELLIGENCE: THEORY AND APPLICATIONS, 1999, 1625 : 684 - 685
12345