Multi-Layer Perceptron with Glial Network for Solving Two-Spiral Problem

• IKUTA Chihiro

  Tokushima University

• UWATE Yoko

  Tokushima University

• NISHIO Yoshifumi

  Tokushima University

Abstract

In this study, we propose a multi-layer perceptron with a glial network which is inspired from the features of glias in the brain. All glias in the proposed network generate independent oscillations, and the oscillations propagate through the glial network with attenuation. We apply the proposed network to the two-spiral problem. Computer simulations show that the proposed network gains a better performance than the conventional multi-layer perceptron.

Journal

• IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

  IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E94-A (9), 1864-1867, 2011

  The Institute of Electronics, Information and Communication Engineers

Keywords

• multi-layer perceptron
• back propagation
• glia
• glial network
• two-spiral problem

Details

• CRID: 1390001206312137088
• NII Article ID: 10030190917
• NII Article ID: 130002133490
• NII Book ID: AA10826239
• DOI: 10.1587/transfun.e94.a.1864
• ISSN: 17451337
• ISSN: 09168508
• Web Site: http://www.jstage.jst.go.jp/article/transfun/E94.A/9/E94.A_9_1864/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed