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
Kertas kerja ini membentangkan dua kaedah pembelajaran kompetitif dengan objektif untuk mengelakkan pergantungan awal vektor berat (rujukan). Yang pertama dipanggil algoritma pembelajaran refraktori dan kompetitif. Algoritma mempunyai tempoh refraktori: Setelah sel telah dicetuskan, unit pemenang yang sepadan dengan sel tidak dipilih sehingga tempoh masa tertentu telah berlalu. Oleh itu, unit tertentu tidak menjadi pemenang pada peringkat awal pemprosesan. Yang kedua dinamakan algoritma pembelajaran kreatif dan kompetitif. Algoritma dibentangkan seperti berikut: Pertama, hanya satu unit output disediakan pada peringkat awal, dan vektor berat mengikut unit dikemas kini di bawah pembelajaran kompetitif. Seterusnya, unit output dicipta secara berurutan kepada nombor yang telah ditetapkan berdasarkan kriteria ralat partition, dan pembelajaran kompetitif dijalankan sehingga syarat penamatan dipenuhi. Akhir sekali, kami membincangkan algoritma yang mempunyai sedikit pergantungan pada nilai awal dan membandingkannya dengan algoritma yang dicadangkan. Keputusan eksperimen dibentangkan untuk menunjukkan bahawa kaedah yang dicadangkan adalah berkesan dalam kes herotan purata.
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.
Salinan
Michiharu MAEDA, Hiromi MIYAJIMA, "Competitive Learning Methods with Refractory and Creative Approaches" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 9, pp. 1825-1833, September 1999, doi: .
Abstract: This paper presents two competitive learning methods with the objective of avoiding the initial dependency of weight (reference) vectors. The first is termed the refractory and competitive learning algorithm. The algorithm has a refractory period: Once the cell has fired, a winner unit corresponding to the cell is not selected until a certain amount of time has passed. Thus, a specific unit does not become a winner in the early stage of processing. The second is termed the creative and competitive learning algorithm. The algorithm is presented as follows: First, only one output unit is prepared at the initial stage, and a weight vector according to the unit is updated under the competitive learning. Next, output units are created sequentially to a prespecified number based on the criterion of the partition error, and competitive learning is carried out until the ternimation condition is satisfied. Finally, we discuss algorithms which have little dependence on the initial values and compare them with the proposed algorithms. Experimental results are presented in order to show that the proposed methods are effective in the case of average distortion.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_9_1825/_p
Salinan
@ARTICLE{e82-a_9_1825,
author={Michiharu MAEDA, Hiromi MIYAJIMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Competitive Learning Methods with Refractory and Creative Approaches},
year={1999},
volume={E82-A},
number={9},
pages={1825-1833},
abstract={This paper presents two competitive learning methods with the objective of avoiding the initial dependency of weight (reference) vectors. The first is termed the refractory and competitive learning algorithm. The algorithm has a refractory period: Once the cell has fired, a winner unit corresponding to the cell is not selected until a certain amount of time has passed. Thus, a specific unit does not become a winner in the early stage of processing. The second is termed the creative and competitive learning algorithm. The algorithm is presented as follows: First, only one output unit is prepared at the initial stage, and a weight vector according to the unit is updated under the competitive learning. Next, output units are created sequentially to a prespecified number based on the criterion of the partition error, and competitive learning is carried out until the ternimation condition is satisfied. Finally, we discuss algorithms which have little dependence on the initial values and compare them with the proposed algorithms. Experimental results are presented in order to show that the proposed methods are effective in the case of average distortion.},
keywords={},
doi={},
ISSN={},
month={September},}
Salinan
TY - JOUR
TI - Competitive Learning Methods with Refractory and Creative Approaches
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1825
EP - 1833
AU - Michiharu MAEDA
AU - Hiromi MIYAJIMA
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 1999
AB - This paper presents two competitive learning methods with the objective of avoiding the initial dependency of weight (reference) vectors. The first is termed the refractory and competitive learning algorithm. The algorithm has a refractory period: Once the cell has fired, a winner unit corresponding to the cell is not selected until a certain amount of time has passed. Thus, a specific unit does not become a winner in the early stage of processing. The second is termed the creative and competitive learning algorithm. The algorithm is presented as follows: First, only one output unit is prepared at the initial stage, and a weight vector according to the unit is updated under the competitive learning. Next, output units are created sequentially to a prespecified number based on the criterion of the partition error, and competitive learning is carried out until the ternimation condition is satisfied. Finally, we discuss algorithms which have little dependence on the initial values and compare them with the proposed algorithms. Experimental results are presented in order to show that the proposed methods are effective in the case of average distortion.
ER -