Directly searching algorithm for multi-layer feed-forward artificial neural networks

Jishou Xing; Xinyi Wang; Weimin Zhang; Chunguang Xu; Keyong Wang

Directly searching algorithm for multi-layer feed-forward artificial neural networks

Jishou Xing^*, Xinyi Wang, Weimin Zhang, Chunguang Xu, Keyong Wang

^*此作品的通讯作者

Beijing Institute of Technology

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

This paper presents a new learning algorithm for multi-layer feed-forward artificial neural networks. The subject transforms into an optimal value of the multivariate function through taking the error square sum of all output unit on all samples as objective function, that is multivariate function of weighting coefficient Using batch method of the output error and step-changing directly adjusting method of the weight, the algorithm has fast learning speed and high precision.

源语言	英语
页（从-至）	189-193
页数	5
期刊	Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
卷	17
期	2
出版状态	已出版 - 1997

其它文件与链接

链接到 Scopus 的出版物

引用此

@article{529ce59394e74ed08d59bb0a19c7ef18,

title = "Directly searching algorithm for multi-layer feed-forward artificial neural networks",

abstract = "This paper presents a new learning algorithm for multi-layer feed-forward artificial neural networks. The subject transforms into an optimal value of the multivariate function through taking the error square sum of all output unit on all samples as objective function, that is multivariate function of weighting coefficient Using batch method of the output error and step-changing directly adjusting method of the weight, the algorithm has fast learning speed and high precision.",

keywords = "Artificial neural networks, Fault diagnosis, Monitoring, Optimum algorithm",

author = "Jishou Xing and Xinyi Wang and Weimin Zhang and Chunguang Xu and Keyong Wang",

year = "1997",

language = "English",

volume = "17",

pages = "189--193",

journal = "Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology",

issn = "1001-0645",

publisher = "Beijing Institute of Technology",

number = "2",

}

TY - JOUR

T1 - Directly searching algorithm for multi-layer feed-forward artificial neural networks

AU - Xing, Jishou

AU - Wang, Xinyi

AU - Zhang, Weimin

AU - Xu, Chunguang

AU - Wang, Keyong

PY - 1997

Y1 - 1997

N2 - This paper presents a new learning algorithm for multi-layer feed-forward artificial neural networks. The subject transforms into an optimal value of the multivariate function through taking the error square sum of all output unit on all samples as objective function, that is multivariate function of weighting coefficient Using batch method of the output error and step-changing directly adjusting method of the weight, the algorithm has fast learning speed and high precision.

AB - This paper presents a new learning algorithm for multi-layer feed-forward artificial neural networks. The subject transforms into an optimal value of the multivariate function through taking the error square sum of all output unit on all samples as objective function, that is multivariate function of weighting coefficient Using batch method of the output error and step-changing directly adjusting method of the weight, the algorithm has fast learning speed and high precision.

KW - Artificial neural networks

KW - Fault diagnosis

KW - Monitoring

KW - Optimum algorithm

UR - http://www.scopus.com/inward/record.url?scp=71149106258&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:71149106258

SN - 1001-0645

VL - 17

SP - 189

EP - 193

JO - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

JF - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

IS - 2

ER -

Directly searching algorithm for multi-layer feed-forward artificial neural networks

摘要

其它文件与链接

指纹

引用此