Presentation 1996/3/18
Neocognitron Applied to Handwritten Digit Recognition : Evaluation with ETL Character Database
Ken-ichi NAGAHARA, Hayaru SHOUNO, Kunihiko FUKUSHIMA, Masato OKADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) 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%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neocognitron / learning method for recognition cells / recognition rate / threshold / character database ETL-1
Paper # NC-95-149
Date of Issue

Conference Information
Committee NC
Conference Date 1996/3/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Neocognitron Applied to Handwritten Digit Recognition : Evaluation with ETL Character Database
Sub Title (in English)
Keyword(1) neocognitron
Keyword(2) learning method for recognition cells
Keyword(3) recognition rate
Keyword(4) threshold
Keyword(5) character database ETL-1
1st Author's Name Ken-ichi NAGAHARA
1st Author's Affiliation Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University()
2nd Author's Name Hayaru SHOUNO
2nd Author's Affiliation Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University
3rd Author's Name Kunihiko FUKUSHIMA
3rd Author's Affiliation Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University
4th Author's Name Masato OKADA
4th Author's Affiliation Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University
Date 1996/3/18
Paper # NC-95-149
Volume (vol) vol.95
Number (no) 598
Page pp.pp.-
#Pages 7
Date of Issue