Research on calculating method of hidden layer nodes in BP network

被引：0
|
作者：
Li, Shifeng [1 ]
Qiu, Zhanzhi [1 ]
机构：
[1] Dalian Jiaotong Univ, Sch Mech Engn, Dalian 116028, Peoples R China
来源：
2015 27TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC) | 2015年
关键词：
HP Network; the Number of Hidden Layer Nodes; Traditional Method; Genetic Algorithm and Dimension Projection Algorithm; NEURAL-NETWORK;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
According to the problem of time consuming in BP network hidden layer nodes number calculation by the traditional method, we propose the dimension projection algorithm. The hidden layer nodes calculation process of traditional method and genetic algorithm are analyzed, the dimension projection algorithm has been proposed, and the calculation process and parameter setting are amplified. We respectively use traditional method, genetic algorithm and dimension projection algorithm to calculate the number of single or double layer BP network hidden nodes of Iris dataset, Leaf dataset and 100 plant species leaves dataset. The simulation results show that the accuracy of dimension projection algorithm and traditional method are close, and the dimension projection algorithm greatly reduces the time consumption.
引用
收藏
页码：2936 / 2940
页数：5
相关论文
共 50 条
  • [1] Research on the Prediction Method of Centrifugal Pump Performance Based on a Double Hidden Layer BP Neural Network
    Han, Wei
    Nan, Lingbo
    Su, Min
    Chen, Yu
    Li, Rennian
    Zhang, Xuejing
    ENERGIES, 2019, 12 (14):
  • [2] The Design of Image Compression with BP Neural Network Based on the Dynamic Adjusting Hidden Layer Nodes
    Li Jing
    Wu Xinhui
    Qin Changhai
    Zhao Jing
    MATERIALS SCIENCE AND INFORMATION TECHNOLOGY, PTS 1-8, 2012, 433-440 : 3797 - +
  • [3] Learning algorithm for designing hidden layer nodes of feedforward neural network
    Fuzhou Univ, Fuzhou, China
    Tien Tzu Hsueh Pao, 11 (126-128):
  • [4] Optimizing hidden layer node number of BP network to estimate fetal weight
    Su, Juan
    Zou, Yuanwen
    Lin, Jiangli
    Wang, Tianfu
    Li, Deyu
    Xie, Tao
    MIPPR 2007: MEDICAL IMAGING, PARALLEL PROCESSING OF IMAGES, AND OPTIMIZATION TECHNIQUES, 2007, 6789
  • [5] A construction method of feedforward neural network for selecting effective hidden nodes
    Su, H
    Zhao, B
    1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 1901 - 1906
  • [6] Optimization method for hidden layer nodes of WNN based on rough set reduction
    Meng, Y.-B. (mengyuebo@163.com), 1600, Northeast University (29):
  • [7] A SELF-ADJUSTING THE NUMBER OF HIDDEN LAYER NEURON ALGORITHM BASED ON BP NETWORK
    Gong, Ningsheng
    Zhou, Mingyu
    Qian, Chunyang
    COMPUTATIONAL INTELLIGENCE: FOUNDATIONS AND APPLICATIONS: PROCEEDINGS OF THE 9TH INTERNATIONAL FLINS CONFERENCE, 2010, 4 : 1017 - 1023
  • [8] Research on the Method of MAP Evaluating Based on BP Network
    Yuan Yan
    Cao Le
    MECHANICAL ENGINEERING AND GREEN MANUFACTURING II, PTS 1 AND 2, 2012, 155-156 : 265 - 269
  • [9] Research of color matching method based on BP network
    Guo, Maozu, 1600, Sci Press (23):
  • [10] A METHOD TO REDUCE REDUNDANT HIDDEN NODES
    SEKITA, I
    KURITA, T
    CHIU, DKY
    ASOH, H
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1994, E77D (04) : 443 - 449
12345