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
계층화된 신경망에서 역전파(BP) 학습의 특징 추출 효율성을 높이기 위해, 모델 전환 맵을 변경하지 않고 기능 모델을 변경하는 것이 제안되었습니다. 모델 전환에는 채널 융합에 의한 지도 보존 단위 감소 또는 채널 설치에 의한 단위 추가가 포함됩니다. 채널 융합을 통해 모델 크기를 줄이기 위해 중복 채널 탐지를 위한 두 가지 기준을 다루고 지도 보존을 위한 로컬 링크 가중치 보상을 공식화합니다. 전환된 모델의 맵 간 불일치의 상한값을 도출하여 전환 모델 후보 선정 시 통일된 기준으로 사용합니다. 실험에서는 특징 추출의 비효율성을 돕기 위해 이미지 텍스처 분류를 위한 계층형 네트워크 모델의 BP 훈련 중에 모델 전환이 사용되었습니다. 결과는 중복 채널의 융합 및 재설치, 지도 보존을 위한 채널 융합에 대한 가중치 보상, 모델 선택을 위한 통일된 기준의 사용이 모두 일반화 능력 향상과 빠른 학습에 효과적인 것으로 나타났습니다. 또한, 모델과 맵의 동시 최적화를 위해 모델 전환을 사용할 수 있는 가능성에 대해 논의합니다.
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
Keisuke KAMEYAMA, Yukio KOSUGI, "Neural Network Model Switching for Efficient Feature Extraction" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 10, pp. 1372-1383, October 1999, doi: .
Abstract: In order to improve the efficiency of the feature extraction of backpropagation (BP) learning in layered neural networks, model switching for changing the function model without altering the map is proposed. Model switching involves map preserving reduction of units by channel fusion, or addition of units by channel installation. For reducing the model size by channel fusion, two criteria for detection of the redundant channels are addressed, and the local link weight compensations for map preservation are formulated. The upper limits of the discrepancies between the maps of the switched models are derived for use as the unified criterion in selecting the switching model candidate. In the experiments, model switching is used during the BP training of a layered network model for image texture classification, to aid its inefficiency of feature extraction. The results showed that fusion and re-installation of redundant channels, weight compensations on channel fusion for map preservation, and the use of the unified criterion for model selection are all effective for improved generalization ability and quick learning. Further, the possibility of using model switching for concurrent optimization of the model and the map will be discussed.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_10_1372/_p
부
@ARTICLE{e82-d_10_1372,
author={Keisuke KAMEYAMA, Yukio KOSUGI, },
journal={IEICE TRANSACTIONS on Information},
title={Neural Network Model Switching for Efficient Feature Extraction},
year={1999},
volume={E82-D},
number={10},
pages={1372-1383},
abstract={In order to improve the efficiency of the feature extraction of backpropagation (BP) learning in layered neural networks, model switching for changing the function model without altering the map is proposed. Model switching involves map preserving reduction of units by channel fusion, or addition of units by channel installation. For reducing the model size by channel fusion, two criteria for detection of the redundant channels are addressed, and the local link weight compensations for map preservation are formulated. The upper limits of the discrepancies between the maps of the switched models are derived for use as the unified criterion in selecting the switching model candidate. In the experiments, model switching is used during the BP training of a layered network model for image texture classification, to aid its inefficiency of feature extraction. The results showed that fusion and re-installation of redundant channels, weight compensations on channel fusion for map preservation, and the use of the unified criterion for model selection are all effective for improved generalization ability and quick learning. Further, the possibility of using model switching for concurrent optimization of the model and the map will be discussed.},
keywords={},
doi={},
ISSN={},
month={October},}
부
TY - JOUR
TI - Neural Network Model Switching for Efficient Feature Extraction
T2 - IEICE TRANSACTIONS on Information
SP - 1372
EP - 1383
AU - Keisuke KAMEYAMA
AU - Yukio KOSUGI
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 1999
AB - In order to improve the efficiency of the feature extraction of backpropagation (BP) learning in layered neural networks, model switching for changing the function model without altering the map is proposed. Model switching involves map preserving reduction of units by channel fusion, or addition of units by channel installation. For reducing the model size by channel fusion, two criteria for detection of the redundant channels are addressed, and the local link weight compensations for map preservation are formulated. The upper limits of the discrepancies between the maps of the switched models are derived for use as the unified criterion in selecting the switching model candidate. In the experiments, model switching is used during the BP training of a layered network model for image texture classification, to aid its inefficiency of feature extraction. The results showed that fusion and re-installation of redundant channels, weight compensations on channel fusion for map preservation, and the use of the unified criterion for model selection are all effective for improved generalization ability and quick learning. Further, the possibility of using model switching for concurrent optimization of the model and the map will be discussed.
ER -