Neocognitron Applied to Handwritten Digit Recognition : Evaluation with ETL Character Database

  • NAGAHARA Ken-ichi
    Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University
  • SHOUNO Hayaru
    Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University
  • FUKUSHIMA Kunihiko
    Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University
  • OKADA Masato
    Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University

Bibliographic Information

Other Title
  • ネオコグニトロンの実用化 : ETL文字データベースによる評価

Search this article

Description

The neocognitron is a neural network model which has the ability to recognize patterns. In our previous work, we obtained a recognition rate of 92.7% for handwritten digits in the ETL-1 database by using a high threshold for feature-extracting cells in the learning phase and a lower threshold in the recognition phase. In this paper, we changed learning method of the highest stage, and increased the number of the training patterns so that we obtained a recognition rate of 97.4%.

Journal

Citations (1)*help

See more

References(6)*help

See more

Details 詳細情報について

  • CRID
    1570291227539117184
  • NII Article ID
    110003233139
  • NII Book ID
    AN10091178
  • Text Lang
    ja
  • Data Source
    • CiNii Articles

Report a problem

Back to top