Research on DBN Network Structure Determination Method Based on Wolves Algorithm

ZHOU Xian-quan; SONG Wei

Chinese

您当前的位置：

首页 >

文章列表页 >

Research on DBN Network Structure Determination Method Based on Wolves Algorithm

更新时间：2026-09-04

- Research on DBN Network Structure Determination Method Based on Wolves Algorithm
- Vol. 35, Issue 7, Pages: 28-34(2018)
- 作者机构：
  
  江南大学物联网工程学院,江苏,无锡,214122
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2018
- 稿件说明：
移动端阅览
周贤泉, 宋威. 基于狼群算法的DBN网络结构确定方法研究[J]. 微电子学与计算机, 2018, 35(7): 28-34.

ZHOU Xian-quan, SONG Wei. Research on DBN Network Structure Determination Method Based on Wolves Algorithm[J]. 2018, 35(7): 28-34.
周贤泉, 宋威. 基于狼群算法的DBN网络结构确定方法研究[J]. 微电子学与计算机, 2018, 35(7): 28-34. DOI：

ZHOU Xian-quan, SONG Wei. Research on DBN Network Structure Determination Method Based on Wolves Algorithm[J]. 2018, 35(7): 28-34. DOI：

摘要

由于深度信念网络(DBN)结构难以确定

提出运用狼群算法确定DBN每层神经元个数

K-means聚类准确性确定是否增加隐含层的方法确定DBN结构.根据狼群算法以最小化所有样本重构误差的平方和为目标函数来确定DBN每层神经元的个数

以确定DBN的初步结构.为了检验DBN结构的有效性

利用DBN提取的数据特征进行聚类测试

进一步根据聚类结果来修正DBN

以获取DBN的最佳结构.实验中选取Iris数据集进行聚类测试

其结果表明

通过所提出的方法获取的DBN有效结构来处理原始数据

能够提高聚类的准确性.

Abstract

Its difficult to determine the structure of deep belief network (DBN)

so raise the method that use the wolves algorithm to determine the number of DBN per layer of neurons

and K-means Clustering Accuracy Determines whether or not to increase the hidden layer method. According to the minimal reconstruction error function of wolves algorithm

it can work out the quantity of each neuron

so as to determine the initial structure of the DBN. In order to verify the effectiveness of the DBN structure

using DBN to extract the data characteristics of the clustering test

so can get the final structure of the DBN. The Iris dataset was tested in the experiment

the results show that the proposed method handles the raw data by the effective structure of the DBN obtained and improve the accuracy of clustering.

关键词

Keywords

references

Tokdar S T, Kass R E. Importance sampling: a review[J]. Wiley Interdisciplinary Reviews Computational Statistics, 2010, 2(1):54-60. DOI: 54

Oxford Benardos P G, Vosniakos G C. Optimizing feedforward artificial neural network architecture[M]. Oxford, Pergamon Press, Inc. 2007.

Gao Daqi. Research on the structure of three layer neural network of teachers with linear basic function[J]. Journal of Circuits and Systems, 1997, 21(3):31-37. DOI: 31

Beijing Wang Xue. Intelligent testing of tests[M]. Beijing: Qinghua University Press, 2008.

Cambridge, Massachusetts, United States Schölkopf B, Platt J, Hofmann T. Greedy layer-wise training of deep networks[M]. Cambridge, Massachusetts, United States, MIT Press, 2007:153-160. DOI: 153

Salakhutdinov R, Murray I. On the quantitative analysis of deep belief networks[C]// International Conference on Machine Learning. ACM, 2008: 872-879.

Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507. DOI: 504

Hinton G E. Learning multiple layers of representation.[J]. Trends in Cognitive Sciences, 2007, 11(10):428-432. DOI: 428

Liu Kai, Zhang Li-min, Sun Yongwei. RBM optimization design based on genetic algorithm[J]. Microelectronics and Computer, 2005, 35 (21) :660-662. DOI: 660

Hinton G E. A practical guide to training restricted boltzmann machines[J]. Momentum, 2012, 9(1):599-619. DOI: 599

Li Fei, Guang GaoXiao, Wan Kaifang. Research on RBM training algorithm based on dynamic gibbs sampling[J]. Acta Automatica Sinica, 2016, 42(6):931-942. DOI: 931

Bengio Y. Learning deep architectures for AI[J]. Foundations and trends in Machine Learning, 2009, 2(1):1-127. DOI: 1

Liu Liqing, Ding Qiaolin, Zhang Tiefeng. Influence of data preprocessing method on fuzzy C - means clustering[J]. Electric Power Science and Engineering, 2011, 27(8):24-27. DOI: 24

Bengio Y, Delalleau O. Justifying and generalizing contrastive divergence[J]. Neural Computation, 1989, 21(6):1601-1605. DOI: 1601

Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 1989, 18(7):1527-1554. DOI: 1527

吴虎胜, 张凤鸣, 吴庐山.一种新的群体智能算法-狼群算法[J].系统工程与电子技术, 2013, 35(11):2430-2438. DOI: 2430

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Simulation on the DC characteristics of double heterojunction p-GaN HEMT with AlN/GaN hybrid buffer layer

Research on assembly action recognition based on MSS-YOLO-MPHands fusion architecture

High gain stability high temperature operational amplifier based on reverse body bias

A review of large model development: technological evolution from BERT to Deepseek

A feature-oriented context understanding and slice analysis network for tuberculosis detection

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰