Heuristic Optimization Using Long, Medium, and Short Term Memories

• Junichi Murata

  Kyushu University

• Tetsuji Fuchikami

  Kyushu University

• Kotaro Hirasawa

  Kyushu University

Bibliographic Information

Other Title

• 長・中・短期記憶を用いた発見的最適化法
• チョウチュウ タンキ キオク オ モチイタ ハッケンテキ サイテキ カホウ

Abstract

An optimization method is proposed for unconstrained optimization problems, including neural network training. To avoid falling into local optima, the method is based on stochastic search and performs diversified and intensified searches alternatingly. Besides, for more efficient search of the solution space, it utilizes its history of searching which is stored in long, medium and short term memories and controls the diversification and intensification of the search. The method includes minimum number of adjustable parameters aiming at a generic method that does not need much parameter tuning. An example shows that the method can find the global optimum irrespective to the initial solutions.

Journal

• IEEJ Transactions on Electronics, Information and Systems

  IEEJ Transactions on Electronics, Information and Systems 118 (9), 1315-1321, 1998

  The Institute of Electrical Engineers of Japan

Keywords

• 最適化
• 集中・分散制御
• 長・中・短期記憶

Details

• CRID: 1390282679585107584
• NII Article ID: 10002814924
• NII Article ID: 130006844159
• NII Book ID: AN10065950
• DOI: 10.1541/ieejeiss1987.118.9_1315
• ISSN: 13488155
• ISSN: 03854221
• NDL BIB ID: 4548610
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I4548610
• Web Site: https://www.jstage.jst.go.jp/article/ieejeiss1987/118/9/118_9_1315/_pdf
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed