Le QV,et al.Building high-level features using large scale unsupervised learning[A].Proceedings of IEEE International Conference on Acoustics,Speech,and Signal Processing[C].USA:IEEE,2013.8595-8598.
[2]
H Goh,et al.Unsupervised and supervised visual codes with restricted Boltzmann machines[A].Proceedings of European Conference on Computer Vision[C].Heidelberg Berlin:Springer,2012.298-311.
[3]
R Mittelman,et al.Weakly supervised learning of mid-level features with beta-Bernoulli process restricted Boltzmann machines[A].Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition[C].USA:IEEE,2013.476-483.
[4]
M Ranzato,et al.On deep generative models with applications to recognition[A].Proceedings of IEEE Conference on Computer Vision and Pattern Recognition[C].USA:IEEE,2011.2857-2864.
[5]
H Lee,et al.Unsupervised learning of hierarchical representations with convolutional deep belief networks[J].Communications of the ACM,2011,54(10):95-103.
[6]
Mohamed,et al.Acoustic modeling using deep belief networks[J].IEEE Transactions on Audio,Speech,and Language Processing,2012,20(1):14-22.
[7]
G E Hinton.Training products of experts by minimizing contrastive divergence[J].Neural computation,2002,14(8):1771-1800.
[8]
M Welling,et al.Exponential family harmoniums with an application to information retrieval[A].Advances in Neural Information Processing Systems[C].Cambridge:MIT Press,2004.1481-1488.
[9]
Sinha N K,Griscik M P.A stochastic approximation method[J].IEEE Transactions on Systems,Man and Cybernetics,1971,4:338-344.
[10]
L Younes.On the convergence of Markovian stochastic algorithms with rapidly decreasing ergodicity rates[J].Stochastics:An International Journal of Probability and Stochastic Processes,1999,65(3-4):177-228.
[11]
A Yuille.The convergence of contrastive divergences[J].Convergence,2006,3:4.
[12]
A Fischer,C Igel.Bounding the bias of contrastive divergence learning[J].Neural Computation,2011,23(3):664-673.
[13]
Dumitru Erhan.Variations on the MNIST digits[DB/OL].http://www.iro.umontreal.ca/～lisa/twiki/bin/view.cgi/Public/MnistVariations,2012-10-23.
[14]
V Nair,G E Hinton.Implicit mixtures of restricted Boltzmann machines[A].Advances in Neural Information Processing Systems[C].Cambridge:MIT Press,2008.1145-1152.
[15]
H Larochelle,Y Bengio.Classification using discriminative restricted Boltzmann machines[A].Proceedings of International Conference on Machine Learning[C].New York:ACM,2008.536-543.
[16]
K Sohn,et al.Learning and selecting features jointly with point-wise gated Boltzmann machines[A].Proceedings of International Conference on Machine Learning[C].New York:ACM,2013.217-225.
[17]
P Vincent,et al.Extracting and composing robust features with denoising autoencoders[A].Proceedings of International Conference on Machine Learning[C].New York:ACM,2008.1096-1103.
[18]
S Rifai,et al.Contractive auto-encoders:Explicit invariance during feature extraction[A].Proceedings of International Conference on Machine Learning[C].New York:ACM,2011.833-840.
