A genetic-algorithms based evolutionary computational neural network for modelling spatial interaction data

被引:33
作者
Fischer, MM
Leung, Y
机构
[1] Univ Econ & Business Adm, Dept Econ & Social Geog, A-1090 Vienna, Austria
[2] Austrian Acad Sci, Inst Urban & Reg Res, A-1010 Vienna, Austria
[3] Chinese Univ Hong Kong, Dept Geog, Shatin, NT, Hong Kong
[4] Chinese Univ Hong Kong, Ctr Environm Studies, Shatin, NT, Hong Kong
关键词
D O I
10.1007/s001680050082
中图分类号
F [经济];
学科分类号
02 ;
摘要
Building a feedforward computational neural network model (CNN) involves two distinct tasks: determination of the network topology and weight estimation. The specification of a problem adequate network topology is a key issue and the primary focus of this contribution. Up to now, this issue has been either completely neglected in spatial application domains, or tackled by search heuristics (see Fischer and Gopal 1994). With the view of modelling interactions over geographic space, this paper considers this problem as a global optimization problem and proposes a novel approach that embeds backpropagation learning into the evolutionary paradigm of genetic algorithms. This is accomplished by interweaving a genetic search for finding an optimal CNN topology with gradient-based backpropagation learning for determining the network parameters. Thus, the model builder will be relieved of the burden of identifying appropriate CNN-topologies that will allow a problem to be solved with simple, but powerful learning mechanisms, such as backpropagation of gradient descent errors. The approach has been applied to the family of three inputs, single hidden layer, single output feedforward CNN models using interregional telecommunication traffic data for Austria, to illustrate its performance and to evaluate its robustness.
引用
收藏
页码:437 / 458
页数:22
相关论文
共 39 条
  • [1] [Anonymous], GEOGRAPHICAL INFORM, DOI DOI 10.1007/978-3-642-77500-0_10
  • [2] [Anonymous], 1993, GENETIC PROGRAMMING
  • [3] Bishop C. M., 1995, Neural networks for pattern recognition
  • [4] CAUDELL TP, 1989, PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON GENETIC ALGORITHMS, P370
  • [5] De Jong K. A., 1975, ANAL BEHAV CLASS GEN
  • [6] FINNOFF W, 1993, ADV NEURAL INFORMATI, V5, P459
  • [7] ARTIFICIAL NEURAL NETWORKS - A NEW APPROACH TO MODELING INTERREGIONAL TELECOMMUNICATION FLOWS
    FISCHER, MM
    GOPAL, S
    [J]. JOURNAL OF REGIONAL SCIENCE, 1994, 34 (04) : 503 - 527
  • [8] Fischer MM, 1997, GEOGRAPHICAL SYSTEMS, V4, P195
  • [9] FISCHER MM, 1998, IN PRESS ENV PLANN A
  • [10] Fogel D.B., 1995, EVOLUTIONARY COMPUTA