|本期目录/Table of Contents|

[1]张逾傲,胡觉亮.随机径向基函数神经网络的收敛性分析[J].浙江理工大学学报,2019,41-42(自科六):835-840.
 ZHANG Yuao,HU Jueliang.Convergence analysis of stochastic radial basis function neural networks[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科六):835-840.
点击复制

随机径向基函数神经网络的收敛性分析()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第41-42卷
期数:
2019年自科六期
页码:
835-840
栏目:
出版日期:
2019-10-31

文章信息/Info

Title:
Convergence analysis of stochastic radial basis function neural networks
文章编号:
1673-3851 (2019) 11-0835-06
作者:
张逾傲胡觉亮
浙江理工大学理学院,杭州 310018
Author(s):
ZHANG Yuao HU Jueliang
School of Sciences, Zhejiang Sci-Tech University, Hangzhou 310018, China
关键词:
神经网络蒙特卡罗方法收敛性分析连续函数径向基函数随机径向基函数
分类号:
TP391
文献标志码:
A
摘要:
为了探究随机径向基函数神经网络的函数逼近能力,运用随机权重前馈神经网络收敛性分析的方法对其进行收敛性分析。首先利用广义δ函数的性质构建一个被近似函数的极限积分表达式;其次用蒙特卡罗方法计算这个表达式中的积分,证明随机径向基函数神经网络可以逼近任意连续函数。同时,从理论上分析了随机径向基函数神经网络的收敛特性,发现其收敛误差随着隐藏层神经元节点的增加而逐渐减少,表明其是一个高效的函数逼近器,并且具有处理大数据问题的潜力。

参考文献/References:

[1] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep Convolutional neural networks[C]// Proceedings of the 25th International Conference on Neural Information Processing Systems. New York: Curran Associates, 2012: 1097-1105.
[2] Salkuti S R. Shortterm electrical load forecasting using radial basis function neural networks considering weather factors[J]. Electrical Engineering, 2018, 100(3): 1985-1995.
[3] Werbos P J. Generalization of Backpropagation with application to a recurrent gas market model[J]. Neural Networks, 1988, 1(4):339-356.
[4] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016:97-117.
[5] Schmidt W F, Kraaijveld M A, Duin R P W. Feedforward neural networks with random weights[C]//11th IAPR International Conference on Pattern Recognition. Los Alamitos, CA: IEEE Computer Society, 1992:1-4.
[6] Li M, Wang D H. Insights into randomized algorithms for neural networks: Practical issues and common pitfalls[J]. Information Sciences, 2017, 382/383:170-178.
[7] Wang D H, Li M. Stochastic Configuration Networks: fundamentals and algorithms[J]. IEEE Transactions on Cybernetics, 2017, 47(10):3466-3479.
[8] Igelnik B, Pao Y H. Stochastic choice of basis functions in adaptive function approximation and the functionallink net[J]. IEEE Transactions on Neural Networks, 1995, 6(6):1320-1329.
[9] Tyukin I Y, Prokhorov D V. Feasibility of random basis function approximators for modeling and control[C]//2009 IEEE International Conference on Control Applications. IEEE, 2009:1391-1396.
[10] Ye H L, Cao F L, Wang D H, et al. Building feedforward neural networks with random weights for large scale datasets[J]. Expert Systems with Applications, 2018, 106:233-243.

相似文献/References:

[1]陈巧红,余仕敏,贾宇波.广告点击率预估技术综述[J].浙江理工大学学报,2015,33-34(自科6):851.
 CHEN Qiao hong,YU Shi min,JIA Yu bo.Overview of Advertisement Clickthrough Rate Estimating Techniques[J].Journal of Zhejiang Sci-Tech University,2015,33-34(自科六):851.

备注/Memo

备注/Memo:
收稿日期:2019-06-24
网络出版日期: 2019-10-08
基金项目:国家自然科学基金项目(11771393)
作者简介:张逾傲(1994-),男,浙江龙泉人,硕士研究生,主要从事神经网络方面的研究
通信作者:胡觉亮,E-mail:hujlhz@163.com
更新日期/Last Update: 2019-11-25