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
본 논문에서는 원하는 부울 함수를 구현할 수 있는 이진 신경망의 유연한 학습 알고리즘을 제시합니다. 알고리즘은 유전 알고리즘을 사용하여 숨겨진 레이어 매개변수를 결정합니다. 숨겨진 뉴런의 수를 줄이고 매개변수 분산을 억제할 수 있습니다. 이러한 장점은 기본적인 수치 실험을 통해 검증되었습니다.
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
Masanori SHIMADA, Toshimichi SAITO, "A GA-Based Learning Algorithm for Binary Neural Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E85-A, no. 11, pp. 2544-2546, November 2002, doi: .
Abstract: This paper presents a flexible learning algorithm for the binary neural network that can realize a desired Boolean function. The algorithm determines hidden layer parameters using a genetic algorithm. It can reduce the number of hidden neurons and can suppress parameters dispersion. These advantages are verified by basic numerical experiments.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e85-a_11_2544/_p
부
@ARTICLE{e85-a_11_2544,
author={Masanori SHIMADA, Toshimichi SAITO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A GA-Based Learning Algorithm for Binary Neural Networks},
year={2002},
volume={E85-A},
number={11},
pages={2544-2546},
abstract={This paper presents a flexible learning algorithm for the binary neural network that can realize a desired Boolean function. The algorithm determines hidden layer parameters using a genetic algorithm. It can reduce the number of hidden neurons and can suppress parameters dispersion. These advantages are verified by basic numerical experiments.},
keywords={},
doi={},
ISSN={},
month={November},}
부
TY - JOUR
TI - A GA-Based Learning Algorithm for Binary Neural Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2544
EP - 2546
AU - Masanori SHIMADA
AU - Toshimichi SAITO
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E85-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2002
AB - This paper presents a flexible learning algorithm for the binary neural network that can realize a desired Boolean function. The algorithm determines hidden layer parameters using a genetic algorithm. It can reduce the number of hidden neurons and can suppress parameters dispersion. These advantages are verified by basic numerical experiments.
ER -