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 Martinetz et al이 제안한 신경가스 네트워크의 강도와 관련된 참조 벡터의 초기 종속성을 피하기 위한 목적으로 자기 조직화 신경망의 인접 순위에 따른 새로운 적응 강도를 처리합니다. 본 접근법은 수치 실험을 통해 기존 기술에 비해 평균 왜곡의 효율성을 보여줍니다. 또한 본 접근법을 이미지 데이터에 적용하여 이미지 코딩 시스템으로 활용하는 데 있어 타당성을 검토합니다.
적응, 자기 조직화 신경망, 동네 순위, 배우기, 이미지 코딩
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
Michiharu MAEDA, Hiromi MIYAJIMA, "Adaptation Strength According to Neighborhood Ranking of Self-Organizing Neural Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E85-A, no. 9, pp. 2078-2082, September 2002, doi: .
Abstract: In this paper we treat a novel adaptation strength according to neighborhood ranking of self-organizing neural networks with the objective of avoiding the initial dependency of reference vectors, which is related to the strength in the neural-gas network suggested by Martinetz et al. The present approach exhibits the effectiveness in the average distortion compared to the conventional technique through numerical experiments. Furthermore the present approach is applied to image data and the validity in employing as an image coding system is examined.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e85-a_9_2078/_p
부
@ARTICLE{e85-a_9_2078,
author={Michiharu MAEDA, Hiromi MIYAJIMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Adaptation Strength According to Neighborhood Ranking of Self-Organizing Neural Networks},
year={2002},
volume={E85-A},
number={9},
pages={2078-2082},
abstract={In this paper we treat a novel adaptation strength according to neighborhood ranking of self-organizing neural networks with the objective of avoiding the initial dependency of reference vectors, which is related to the strength in the neural-gas network suggested by Martinetz et al. The present approach exhibits the effectiveness in the average distortion compared to the conventional technique through numerical experiments. Furthermore the present approach is applied to image data and the validity in employing as an image coding system is examined.},
keywords={},
doi={},
ISSN={},
month={September},}
부
TY - JOUR
TI - Adaptation Strength According to Neighborhood Ranking of Self-Organizing Neural Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2078
EP - 2082
AU - Michiharu MAEDA
AU - Hiromi MIYAJIMA
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E85-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2002
AB - In this paper we treat a novel adaptation strength according to neighborhood ranking of self-organizing neural networks with the objective of avoiding the initial dependency of reference vectors, which is related to the strength in the neural-gas network suggested by Martinetz et al. The present approach exhibits the effectiveness in the average distortion compared to the conventional technique through numerical experiments. Furthermore the present approach is applied to image data and the validity in employing as an image coding system is examined.
ER -