基于半监督深度信念网络的图像分类算法研究

计算机科学 ›› 2016, Vol. 43 ›› Issue (Z6): 46-50.doi: 10.11896/j.issn.1002-137X.2016.6A.010

基于半监督深度信念网络的图像分类算法研究

朱常宝,程勇,高强

北京化工大学信息学院北京100029,北京化工大学信息学院北京100029,北京化工大学信息学院北京100029

出版日期:2018-12-01 发布日期:2018-12-01

Research on Image Classification Algorithm Based on Semi-supervised Deep Belief Network

ZHU Chang-bao, CHENG Yong and GAO Qiang

Online:2018-12-01 Published:2018-12-01

摘要/Abstract

摘要： 近年来,深度学习在图像、语音、视频等非结构化数据中获得了成功的应用,已成为机器学习和数据挖掘领域的研究热点。作为一种监督学习模型,成功的深度学习应用往往要求较大的高质量的训练集。基于此,研究了多个受限波尔兹曼机组成的深度信念网络,结合半监督学习的思想,使用较小的训练集提高深度网络模型的分类准确性。分别采用了Knn,SVM和pHash 3种方法来学习非标示数据集,实验结果表明半监督深度信念网络比传统多层受限波尔兹曼机在图像分类准确率方面提高了约3%。

关键词: 半监督学习,深度信念网络,受限波尔兹曼机

Abstract: In recent years,the deep learning to get a successful application in image,voice,video and other unstructured data,has become a hot topic of machine learning and data mining.As a supervised learning model,the successful deep learning applications often require a larger set of high-quality training.Based on this situation,we studied deep belief network composed of more restricted Boltzmann machines,and combined with the thought of semi-supervised learning,we used smaller training set to improve the classification accuracy of depth network model.We used Knn,SVM and pHash three methods to study the non-labeled data set.And the result shows that the semi-supervised deep belief networks increases image classification accuracy by about 3% compared with the traditional network with more restricted Boltzmann machine.

Key words: Semi-supervised,Deep belief networks,Restricted boltzmann machine

朱常宝,程勇,高强. 基于半监督深度信念网络的图像分类算法研究[J]. 计算机科学, 2016, 43(Z6): 46-50. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.010

ZHU Chang-bao, CHENG Yong and GAO Qiang. Research on Image Classification Algorithm Based on Semi-supervised Deep Belief Network[J]. Computer Science, 2016, 43(Z6): 46-50. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.010

参考文献

[1] Hinton G,Deng L,Yu D,et al.Deep neural networks for acoustic modeling in speech recognition:The shared views of four research groups[J].Signal Processing Magazine,2012,29(6):82-97
[2] Mohamed A,Dahl G E,Hinton G.Acoustic modeling using deep belief networks[J].IEEE Trans on Audio,Speech,and Language Processing,2012,20(1):14-22
[3] Roux N L,Bengio Y.Representational power of restricted Boltzmann machines and deep belief networks[J].Neural Computation,2006,20(6):1631-1649
[4] Hinton G E,Osindero S,The Y.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554
[5] Sainath T N,Kingsbury B,Soltau H,et al.Optimization technique to improve training speed of deep belief networks for large speech tash tasks[J].IEEE Trans on Audio,Speech,and Language Processing,2013,1(11):2267-2276
[6] You Z,Wang X,Xu B.Exploring one pass learning for deep neural network training with averaged stochastic gradient descent[C]∥IEEE International Conference on Acoustics,Speech and Signal Processing.2014:6854-6858
[7] Erhan D,Courville A,Bengio Y,et al.Visualizing Higher Layer Features of a Deep Network[C]∥Spotlight presentation and poster at the ICML 2009 Workshop on Learning Feature Hierarchies.Montreal,Canada,2009
[8] Hinton G E.Training products of experts by minimizing contrastive divergence[J].Neural Computation,2002,14(8):1771-1800
[9] Mass A L,Hannum A Y,Lengerich C T,et al.Increasing deep neural network acoustic model size for large vocabulary conti-nuous speech recognition[J].arXiv preprint arXiv:1406.7806,4
[10] Hsu C,Lin C.A comparison on methods for multi-class support vector machines[J].IEEE Transactions on Neural Networks,2002,12:415-425
[11] Zauner.Christoph:Implementation and Benchmarking of Per-ceptual Image Hash Functions[C]∥Master’s thesis,Upper Austria University of Applied Sciences.Hagenberg Campus,2010
[12] Hinton G E.A practical guide to training restricted Boltzmann machines[J].Momentum,2010,9(1):926
[13] Deng W,Qian Y,Fan Y,et al.Stochastic data sweeping for fast DNN training[C]∥Proc of IEEE International Conference on Acoustics,Speech and Signal Processing.2014:240-244
[14] 罗恒.基于协同过滤视角的受限波尔兹曼机研究[D].上海:上海交通大学,2011

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed