Optimal-structure determination of power-activation feed-forward neural net

doi:10.3778/j.issn.1002-8331.2011.02.009

Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (2): 29-31.DOI: 10.3778/j.issn.1002-8331.2011.02.009

• 研究、探讨 • Previous Articles Next Articles

Optimal-structure determination of power-activation feed-forward neural net

ZHANG Yunong¹，GUO Dongsheng¹，TAN Ning²

1.School of Information Science and Technology，Sun Yat-Sen University，Guangzhou 510275，China
2.School of Software，Sun Yat-Sen University，Guangzhou 510275，China

Received:2009-09-28 Revised:2010-05-31 Online:2011-01-11 Published:2011-01-11
Contact: ZHANG Yunong

幂激励前向神经网络最优结构确定算法

张雨浓¹，郭东生¹，谭宁²

1.中山大学信息科学与技术学院，广州 510275
2.中山大学软件学院，广州 510275

通讯作者: 张雨浓

Abstract

Abstract: For a kind of feed-forward neural net with hidden-neurons’ activation-functions being a sequence of power functions，an optimal network-structure determination algorithm is proposed based on the weights-direct-determination method.Computer simulation and verification results indicate that the algorithm can determine the optimal number of hidden-layer neurons automatically，quickly and effectively，which achieves the best approximation ability of the neural net and thus realizes the network-structure optimization.

Key words: power series, feed-forward neural net, hidden-layer neurons, structure optimization, weights direct determination

摘要： 针对一种以幂函数序列为各隐神经元激励函数的前向神经网络，提出了一种基于权值直接确定方法的网络最优结构确定算法。计算机仿真与验证结果表明，该算法能自动、快速、有效地确定网络的最优隐神经元数，达到网络的最佳逼近能力，从而实现网络结构的最优化。

关键词: 幂级数, 前向神经网络, 隐神经元数, 结构最优化, 权值直接确定法

CLC Number:

TP183

ZHANG Yunong¹，GUO Dongsheng¹，TAN Ning². Optimal-structure determination of power-activation feed-forward neural net[J]. Computer Engineering and Applications, 2011, 47(2): 29-31.

张雨浓¹，郭东生¹，谭宁². 幂激励前向神经网络最优结构确定算法[J]. 计算机工程与应用, 2011, 47(2): 29-31.

[1]	DU Yao. Android Malicious Family Detection Algorithm Based on Local Optimization Matching [J]. Computer Engineering and Applications, 2021, 57(8): 84-90.
[2]	CHEN Kefan, LV Na, ZHANG Weilong. Frame structure optimization and analysis of fast dynamic slot assignment MAC protocol [J]. Computer Engineering and Applications, 2015, 51(15): 68-74.
[3]	BU Fanyu1，2, CHEN Zhikui1, ZHANG Qingchen1. Incremental updating method for big data feature learning [J]. Computer Engineering and Applications, 2015, 51(12): 21-26.
[4]	LI Zhanming1, ZHANG Yongjiang1，2, HAN Dahong3. Vector “membership” based fuzzy controller structure optimization [J]. Computer Engineering and Applications, 2014, 50(21): 74-78.
[5]	ZHANG Yunong1，2, LAO Wenchao1, YU Xiaotian1, LI Jun1. Weights and structure determination of two-input power-activation feed-forward neural network [J]. Computer Engineering and Applications, 2012, 48(15): 102-106.
[6]	ZENG Fansong，TENG Qizhi. Application and optimization for Lattice Boltzmann Method in calculation of fluid permeability [J]. Computer Engineering and Applications, 2011, 47(22): 156-159.
[7]	QIAO Xin-yong¹,ZHOU Yun-feng². Method for optimizing structure of neural network in states measuring based on multi-parameters [J]. Computer Engineering and Applications, 2009, 45(8): 236-237.
[8]	TANG Yun-lan^1，2，GAO Yan-fang¹，TAN Xu¹，CHEN Ying-wu¹. Research on structure of multi-layer feed-forward neural network with cross connections [J]. Computer Engineering and Applications, 2009, 45(32): 45-47.
[9]	ZHANG Yu-dong¹,WU Le-nan¹,WU Han-qian². Comparison of neural network and evolutionary algorithm on engineering optimization [J]. Computer Engineering and Applications, 2009, 45(3): 1-6.
[10]	LI Wei-qiang，XU Jian-cheng，YIN Jian-feng. ee colony optimization algorithm for training feed-forward neural networks [J]. Computer Engineering and Applications, 2009, 45(24): 43-45.
[11]	zhengwei chen Peng Yan LiKe Zhuang. E-government Software Research and Application Based on the Ajax Technology [J]. Computer Engineering and Applications, 2007, 43(5期): 196-199.
[12]	XIA Tai-wu¹,LIU Jin-xiang¹,PENG Jing-hua². Method of evolutionary neural computation on traffic of calls [J]. Computer Engineering and Applications, 2007, 43(30): 130-132.
[13]	LIU Jia-lu，LIU Qiong-sun，HU Shang-wei. Back-propagation algorithm based on enlarging error signals [J]. Computer Engineering and Applications, 2007, 43(21): 90-92.

Optimal-structure determination of power-activation feed-forward neural net

幂激励前向神经网络最优结构确定算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 13

Recommended Articles

Metrics