The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
분류 함수는 벡터 세트를 여러 클래스로 매핑합니다. 기계 학습 문제는 부분적으로 정의된 분류 기능에 대한 설계 문제로 처리됩니다. MNIST 손으로 쓴 숫자에 대한 분류 기능을 구현하기 위해 단일 단위 구현, 45단위 구현 및 45단위 ×의 세 가지 아키텍처가 고려됩니다.r 실현. 45개 단위 구현은 45개의 삼항 분류기, 10개의 카운터 및 최대 선택기로 구성됩니다. 이러한 아키텍처의 테스트 정확도는 MNIST 데이터 세트를 사용하여 비교됩니다.
Tsutomu SASAO
Meiji University
Yuto HORIKAWA
Meiji University
Yukihiro IGUCHI
Meiji University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Tsutomu SASAO, Yuto HORIKAWA, Yukihiro IGUCHI, "Classification Functions for Handwritten Digit Recognition" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 8, pp. 1076-1082, August 2021, doi: 10.1587/transinf.2020LOP0002.
Abstract: A classification function maps a set of vectors into several classes. A machine learning problem is treated as a design problem for partially defined classification functions. To realize classification functions for MNIST hand written digits, three different architectures are considered: Single-unit realization, 45-unit realization, and 45-unit ×r realization. The 45-unit realization consists of 45 ternary classifiers, 10 counters, and a max selector. Test accuracy of these architectures are compared using MNIST data set.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020LOP0002/_p
부
@ARTICLE{e104-d_8_1076,
author={Tsutomu SASAO, Yuto HORIKAWA, Yukihiro IGUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={Classification Functions for Handwritten Digit Recognition},
year={2021},
volume={E104-D},
number={8},
pages={1076-1082},
abstract={A classification function maps a set of vectors into several classes. A machine learning problem is treated as a design problem for partially defined classification functions. To realize classification functions for MNIST hand written digits, three different architectures are considered: Single-unit realization, 45-unit realization, and 45-unit ×r realization. The 45-unit realization consists of 45 ternary classifiers, 10 counters, and a max selector. Test accuracy of these architectures are compared using MNIST data set.},
keywords={},
doi={10.1587/transinf.2020LOP0002},
ISSN={1745-1361},
month={August},}
부
TY - JOUR
TI - Classification Functions for Handwritten Digit Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1076
EP - 1082
AU - Tsutomu SASAO
AU - Yuto HORIKAWA
AU - Yukihiro IGUCHI
PY - 2021
DO - 10.1587/transinf.2020LOP0002
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2021
AB - A classification function maps a set of vectors into several classes. A machine learning problem is treated as a design problem for partially defined classification functions. To realize classification functions for MNIST hand written digits, three different architectures are considered: Single-unit realization, 45-unit realization, and 45-unit ×r realization. The 45-unit realization consists of 45 ternary classifiers, 10 counters, and a max selector. Test accuracy of these architectures are compared using MNIST data set.
ER -