Input Variable Selection for Multi-Layer Neural Networks

DOI HANDLE Open Access
  • Murata Junichi
    Department of Electrical and Electronic Systems Engineering, Kyushu University
  • Nakazono Toru
    Department of Electrical and Electronic Systems Engineering, Kyushu University : Master's Program
  • Hirasawa Kotaro
    Department of Electrical and Electronic Systems Engineering, Kyushu University

Bibliographic Information

Other Title
  • 階層型ニューラルネットワークへの入力の選定法

Search this article

Abstract

A method is proposed for selecting relevant input variables to multi-layer neural networks. A minimal set of inputs is selected which is necessary to obtain a network with a good generalization ability and some insight into the input-output relationship. The inputs of network are selected automatically by a combination of constructive and destructive algorithms. The constructive algorithm starts with a minimal input set and adds new inputs if necessary, while the destructive algorithm deletes unnecessary inputs. The main issue addressed here is the measure of input significance used in the constructive algorithm. Some measures are proposed based on mutual infomation and linear correlation paying much attention to the structural constraint imposed on the networks. The experimental results show that the measures are valid and that the derived network with the selected inputs has a good generalization ability.

Journal

Keywords

Details 詳細情報について

  • CRID
    1390009224843519232
  • NII Article ID
    110000579894
  • NII Book ID
    AN10569524
  • DOI
    10.15017/1498360
  • ISSN
    21880891
    13423819
  • HANDLE
    2324/1498360
  • Text Lang
    ja
  • Data Source
    • JaLC
    • IRDB
    • CiNii Articles
  • Abstract License Flag
    Allowed

Report a problem

Back to top