New method for determining weights in neural network

被引：0
|
作者：
Moriya, Yukinobu
Amaya, Kenji
Aoki, Shigeru
机构：
来源：
Nippon Kikai Gakkai Ronbunshu, A Hen/Transactions of the Japan Society of Mechanical Engineers, Part A | 1994年 / 60卷 / 570期
关键词：
Artificial intelligence - Computational methods - Inverse problems - Neural networks;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
A new method to quickly determine weights in a layered neural network is introduced. By making use of the relation between the input of one unit in the (k+1)th layer and the output of all the units in the kth layer, all the weights can be obtained easily provided that the number of units in at least one layer is greater than or equal to the number of teacher sets plus 1. From two examples, it is shown that calculation time required by the new method is much shorter than that of back propagation method.
引用
收藏
页码：574 / 579
相关论文
共 50 条
  • [21] Global optimization of neural network weights
    Hamm, L
    Brorsen, BW
    Hagan, MT
    PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 1228 - 1233
  • [22] New KEMIRA Method for Determining Criteria Priority and Weights in Solving MCDM Problem
    Krylovas, Aleksandras
    Zavadskas, Edmundas Kazimieras
    Kosareva, Natalja
    Dadelo, Stanislav
    INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING, 2014, 13 (06) : 1119 - 1133
  • [23] Induced weights artificial neural network
    Golak, S
    ARTIFICIAL NEURAL NETWORKS: FORMAL MODELS AND THEIR APPLICATIONS - ICANN 2005, PT 2, PROCEEDINGS, 2005, 3697 : 295 - 300
  • [24] A new method to prune the neural network
    Wan, WS
    Hirasawa, K
    Hu, JL
    Jin, CZ
    IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL VI, 2000, : 449 - 454
  • [25] Neural network with multiple connection weights
    Zhang, Jiangshe
    Hu, Junying
    Liu, Junmin
    PATTERN RECOGNITION, 2020, 107
  • [26] New method to prune the neural network
    Wan, Weishui
    Hirasawa, Kotaro
    Hu, Jinglu
    Jin, Chunzhi
    Research Reports on Information Science and Electrical Engineering of Kyushu University, 2000, 5 (01): : 43 - 49
  • [27] An artificial neural network method for combining gene prediction based on equitable weights
    Zhou, You
    Liang, Yanchun
    Hu, Chengquan
    Wang, Liupu
    Shi, Xiaohu
    NEUROCOMPUTING, 2008, 71 (4-6) : 538 - 543
  • [28] The Neural Network Method of Index System and Weights for Highway Tunnel Health Diagnosis
    Xie, Kai-zhong
    Song, Bing-hui
    Wang, C. Hong-wei
    Lv, D. Lin-hai
    SENSORS, MEASUREMENT AND INTELLIGENT MATERIALS, PTS 1-4, 2013, 303-306 : 794 - 798
  • [29] Image Segmentation Method Based on Spiking Neural Network with Adaptive Synaptic Weights
    Zheng, Donghao
    Lin, Xianghong
    Wang, Xiangwen
    2019 IEEE 4TH INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING (ICSIP 2019), 2019, : 1043 - 1049
  • [30] CRITIQUE OF HARVARD METHOD FOR DETERMINING ATOMIC WEIGHTS
    SCOTT, AF
    ANALYTICAL CHEMISTRY, 1961, 33 (09) : A23 - &
12345