Title:
【発明の名称】シフト/不変パターン認識を行う受容野ニューラルネットワーク
Document Type and Number:
Japanese Patent JP2862216
Kind Code:
B2
Abstract:
A neural network system and method of operating same wherein input data are initialized, then mapped onto a predetermined array for learning or recognition. The mapped information is divided into sub-input data or receptive fields, which are used for comparison of the input information with prelearned information having similar features, thereby allowing for correct classification of the input information. The receptive fields are shifted before the classification process, in order to generate a closest match between features which may be shifted at the time of input, and weights of the input information are updated based upon the closest-matching shifted position of the input information.
Inventors:
UEDA TOORU
TOGAWA FUMIO
TOGAWA FUMIO
Application Number:
JP874292A
Publication Date:
March 03, 1999
Filing Date:
January 21, 1992
Export Citation:
Assignee:
SHAAPU KK
International Classes:
G06G7/60; G06N3/00; G06F15/18; G06N99/00; G06V30/10; (IPC1-7): G06F15/18; G06G7/60
Other References:
シャープ技報 ＮＯ．５１ ｐ２５−３０ １９９１ 上田徹、石田康司、荒巻隆志、外田文雄、田中厚夫「ニューラルネットを用いた漢字認識」
Attorney, Agent or Firm:
Shusaku Yamamoto