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
Dalam pengecaman corak menggunakan rangkaian neural, amat sukar bagi penyelidik atau pengguna untuk mereka bentuk seni bina rangkaian neural yang optimum untuk tugas tertentu. Mana-mana jenis seni bina rangkaian saraf boleh mendapatkan ukuran nisbah pengecaman tertentu. Walau bagaimanapun, adalah sukar untuk mendapatkan seni bina rangkaian saraf yang optimum untuk tugas tertentu secara analitikal dalam nisbah pengiktirafan dan keberkesanan latihan. Dalam makalah ini, kaedah evolusi melatih dan mereka bentuk rangkaian neural suapan dicadangkan. Dalam kaedah yang dicadangkan, rangkaian saraf ditakrifkan sebagai satu individu dan rangkaian saraf yang seni binanya sama dengan satu spesies. Rangkaian ini dinilai oleh MSE yang dinormalisasi (Mean Square Error) yang membentangkan prestasi rangkaian untuk corak latihan. Kemudian, seni bina mereka berkembang mengikut peraturan evolusi yang dicadangkan di sini. Seni bina rangkaian saraf, dengan kata lain, spesies, dinilai dengan ukuran kriteria lain berbanding dengan kriteria individu. Kriteria menilai individu yang paling unggul dalam spesies dan kelajuan evolusi spesies. Spesies bertambah atau berkurang saiz populasi mengikut kriteria. Peraturan evolusi menghasilkan seni bina rangkaian saraf yang sedikit berbeza daripada spesies unggul. Kaedah yang dicadangkan, oleh itu, boleh menjana pelbagai seni bina rangkaian saraf. Mereka bentuk dan melatih rangkaian neural yang berfungsi dengan mudah 3
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
Hiroki TAKAHASHI, Masayuki NAKAJIMA, "Evolutional Design and Training Algorithm for Feedforward Neural Networks" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 10, pp. 1384-1392, October 1999, doi: .
Abstract: In pattern recognition using neural networks, it is very difficult for researchers or users to design optimal neural network architecture for a specific task. It is possible for any kinds of neural network architectures to obtain a certain measure of recognition ratio. It is, however, difficult to get an optimal neural network architecture for a specific task analytically in the recognition ratio and effectiveness of training. In this paper, an evolutional method of training and designing feedforward neural networks is proposed. In the proposed method, a neural network is defined as one individual and neural networks whose architectures are same as one species. These networks are evaluated by normalized M. S. E. (Mean Square Error) which presents a performance of a network for training patterns. Then, their architectures evolve according to an evolution rule proposed here. Architectures of neural networks, in other words, species, are evaluated by another measurement of criteria compared with the criteria of individuals. The criteria assess the most superior individual in the species and the speed of evolution of the species. The species are increased or decreased in population size according to the criteria. The evolution rule generates a little bit different architectures of neural network from superior species. The proposed method, therefore, can generate variety of architectures of neural networks. The designing and training neural networks which performs simple 3
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_10_1384/_p
Salinan
@ARTICLE{e82-d_10_1384,
author={Hiroki TAKAHASHI, Masayuki NAKAJIMA, },
journal={IEICE TRANSACTIONS on Information},
title={Evolutional Design and Training Algorithm for Feedforward Neural Networks},
year={1999},
volume={E82-D},
number={10},
pages={1384-1392},
abstract={In pattern recognition using neural networks, it is very difficult for researchers or users to design optimal neural network architecture for a specific task. It is possible for any kinds of neural network architectures to obtain a certain measure of recognition ratio. It is, however, difficult to get an optimal neural network architecture for a specific task analytically in the recognition ratio and effectiveness of training. In this paper, an evolutional method of training and designing feedforward neural networks is proposed. In the proposed method, a neural network is defined as one individual and neural networks whose architectures are same as one species. These networks are evaluated by normalized M. S. E. (Mean Square Error) which presents a performance of a network for training patterns. Then, their architectures evolve according to an evolution rule proposed here. Architectures of neural networks, in other words, species, are evaluated by another measurement of criteria compared with the criteria of individuals. The criteria assess the most superior individual in the species and the speed of evolution of the species. The species are increased or decreased in population size according to the criteria. The evolution rule generates a little bit different architectures of neural network from superior species. The proposed method, therefore, can generate variety of architectures of neural networks. The designing and training neural networks which performs simple 3
keywords={},
doi={},
ISSN={},
month={October},}
Salinan
TY - JOUR
TI - Evolutional Design and Training Algorithm for Feedforward Neural Networks
T2 - IEICE TRANSACTIONS on Information
SP - 1384
EP - 1392
AU - Hiroki TAKAHASHI
AU - Masayuki NAKAJIMA
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 1999
AB - In pattern recognition using neural networks, it is very difficult for researchers or users to design optimal neural network architecture for a specific task. It is possible for any kinds of neural network architectures to obtain a certain measure of recognition ratio. It is, however, difficult to get an optimal neural network architecture for a specific task analytically in the recognition ratio and effectiveness of training. In this paper, an evolutional method of training and designing feedforward neural networks is proposed. In the proposed method, a neural network is defined as one individual and neural networks whose architectures are same as one species. These networks are evaluated by normalized M. S. E. (Mean Square Error) which presents a performance of a network for training patterns. Then, their architectures evolve according to an evolution rule proposed here. Architectures of neural networks, in other words, species, are evaluated by another measurement of criteria compared with the criteria of individuals. The criteria assess the most superior individual in the species and the speed of evolution of the species. The species are increased or decreased in population size according to the criteria. The evolution rule generates a little bit different architectures of neural network from superior species. The proposed method, therefore, can generate variety of architectures of neural networks. The designing and training neural networks which performs simple 3
ER -