In view of the problem of feature extraction for analog circuit fault diagnosis
model of deep belief network (DBN) is introduced in this paper. Comparison experiments on Leapfrog Filter with a group of models including DBN
single hidden layer BP and three hidden layer BP prove that the model of DBN is feasible and effective. Moreover
according to the experiment on band pass filters with methods of wavelet analysis
DBN and single hidden layer BP network
the results show that the ability of feature extraction of DBN is better and the feature of extraction is closer to the essence of data.
关键词
Keywords
references
Bengio Y. Learning deep architectures for AI[J]. Foundations % Trends in Machine Learning, 2009, 2(1): 1-127. DOI: 1
Zhang L, Sun L, Cai X, et al. Analog circuit fault diagnosis based on the wavelet analysis and EM algorithm of limited gaussian mixture model[J]. International Journal of Advancements in Computing Technology, 2013, 10(5): 32-42. DOI: 32
Geoffrey H. Where do features come from?[J]. Cognitive Science A Multidisciplinary Journal, 2013, 38(6): 1078-1101. DOI: 1078
Hinton G E. Training products of experts by minimizing contrastive divergence[J]. Neural Computation, 2002, 14(8): 1771-1800. DOI: 1771
Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507. DOI: 504
Neural Networks Hinton G E. A practical guide to training restricted boltzmann machines[M]. Neural Networks: Tricks of the Trade of the series Lecture Notes in Computer Science, 2012, 9(1): 599-619. DOI: 599