1AREL I,ROSE D C, KARNOWSKI T P. Deep machine learn- ing- A new frontier in artificial intelligence research [ J l- Computational intelligence magazine,2010,5(4) :13-18. 被引量：1
2MARKOFF J. Scientists see promise in deep-learning pro- grams [ N ]. The New York Times, 2012-11-23. 被引量：1
3PLIS S M , HJELM D R,SALAKHUTDINOV R,et al. Deep learning for neuroimaging: a validation study [ J ] Frontiers in neuroscience,2014( 8 ) :229. 被引量：1
4ELFWING S, UCHIBE E, DOYA K. Expected energy-based restricted Boltzmann machine for classification [ J 1- Neural networks, 2015 ( 64 ) : 29 -38. 被引量：1
5MOCANU D C, AMMAR H B. Factored four way conditional restricted Boltzmann machines for activity recognition [ J ]. Pattern recognition letters, 2015 (66) : 100-108. 被引量：1
6LIU P,HAN S Z, MENG Z B,et al. Facial expression rec- ognition via a boosted deep belief network [ C ]//Proc. the 2014 IEEE Conference on Computer Vision and Pattern Recognition. [ S. 1. ] :IEEE ,2014 : 1805-1812. 被引量：1
7HINTON G. Training products of experts by minimizing cont- rastive divergence [ J ]. Neural computation, 2006, 14 ( 8 ) : 1771-1800. 被引量：1
8TIELEMAN T. Training restricted Boltzmann machines using approximations to the likelihood gradient [ C ]//Proc. the 25 th International Conference on Machine learning. [ S. 1. ] : IEEE,2008 : 1064-1071. 被引量：1
9LOPES N, RIBEIRO B. Towards adaptive learning with im- proved convergence of deep belief networks on graphics pro- cessing units [ J ]1. Pattern recognition, 2014,47 ( 1 ) : 114- 127. 被引量：1
