메뉴 건너뛰기




Volumn 47, Issue 1, 2014, Pages 114-127

Towards adaptive learning with improved convergence of deep belief networks on graphics processing units

Author keywords

Adaptive step size; Contrastive divergence; Deep belief networks; Deep learning; GPU computing; Restricted Boltzmann machines

Indexed keywords

ADAPTIVE STEP SIZE; CONTRASTIVE DIVERGENCE; DEEP BELIEF NETWORKS; DEEP LEARNING; GPU COMPUTING; RESTRICTED BOLTZMANN MACHINE;

EID: 84885018698     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patcog.2013.06.029     Document Type: Article
Times cited : (68)

References (34)
  • 1
    • 84885021847 scopus 로고    scopus 로고
    • Giant steps in teaching computers to think like us: 'Neural nets' mimic the ways human minds listen, see and execute
    • November
    • J. Markoff Giant steps in teaching computers to think like us: 'neural nets' mimic the ways human minds listen, see and execute International Herald Tribune 24-25 November 2012 1 8
    • (2012) International Herald Tribune , vol.24-25 , pp. 1-8
    • Markoff, J.1
  • 3
    • 45749110924 scopus 로고    scopus 로고
    • Representational power of restricted Boltzmann machines and deep belief networks
    • N.L. Roux, and Y. Bengio Representational power of restricted Boltzmann machines and deep belief networks Neural Computation 20 6 2008 1631 1649
    • (2008) Neural Computation , vol.20 , Issue.6 , pp. 1631-1649
    • Roux, N.L.1    Bengio, Y.2
  • 6
    • 85032782045 scopus 로고    scopus 로고
    • Deep learning and its applications to signal and information processing
    • D. Yu, and L. Deng Deep learning and its applications to signal and information processing IEEE Signal Processing Magazine 28 1 2011 145 154
    • (2011) IEEE Signal Processing Magazine , vol.28 , Issue.1 , pp. 145-154
    • Yu, D.1    Deng, L.2
  • 7
    • 77955997114 scopus 로고    scopus 로고
    • Deep belief networks are compact universal approximators
    • N.L. Roux, and Y. Bengio Deep belief networks are compact universal approximators Neural Computation 22 8 2010 2192 2207
    • (2010) Neural Computation , vol.22 , Issue.8 , pp. 2192-2207
    • Roux, N.L.1    Bengio, Y.2
  • 8
    • 33745805403 scopus 로고    scopus 로고
    • A fast learning algorithm for deep belief nets
    • DOI 10.1162/neco.2006.18.7.1527
    • G.E. Hinton, S. Osindero, and Y.-W. Teh A fast learning algorithm for deep belief nets Neural Computation 18 7 2006 1527 1554 (Pubitemid 44024729)
    • (2006) Neural Computation , vol.18 , Issue.7 , pp. 1527-1554
    • Hinton, G.E.1    Osindero, S.2    Teh, Y.-W.3
  • 9
    • 77952681438 scopus 로고    scopus 로고
    • A tutorial on stochastic approximation algorithms for training restricted Boltzmann machines and deep belief nets
    • K. Swersky, B. Chen, B. Marlin, N. de Freitas, A tutorial on stochastic approximation algorithms for training restricted Boltzmann machines and deep belief nets, in: Information Theory and Applications Workshop, 2010, pp. 1-10.
    • (2010) Information Theory and Applications Workshop , pp. 1-10
    • Swersky, K.1    Chen, B.2    Marlin, B.3    De Freitas, N.4
  • 13
    • 78149361170 scopus 로고    scopus 로고
    • A high-performance FPGA architecture for restricted Boltzmann machines
    • D. Ly, and P. Chow A high-performance FPGA architecture for restricted Boltzmann machines IEEE Transactions on Neural Networks 21 11 2010 1780 1792
    • (2010) IEEE Transactions on Neural Networks , vol.21 , Issue.11 , pp. 1780-1792
    • Ly, D.1    Chow, P.2
  • 17
    • 78149258346 scopus 로고    scopus 로고
    • Understanding throughput-oriented architectures
    • M. Garland, and D.B. Kirk Understanding throughput-oriented architectures Communications of the ACM 53 11 2010 58 66
    • (2010) Communications of the ACM , vol.53 , Issue.11 , pp. 58-66
    • Garland, M.1    Kirk, D.B.2
  • 19
    • 78650474133 scopus 로고    scopus 로고
    • A Practical Guide to Training Restricted Boltzmann Machines
    • University of Toronto
    • G.E. Hinton, A Practical Guide to Training Restricted Boltzmann Machines, Technical Report, Department of Computer Science, University of Toronto, 2010.
    • (2010) Technical Report, Department of Computer Science
    • Hinton, G.E.1
  • 22
    • 0013344078 scopus 로고    scopus 로고
    • Training products of experts by minimizing contrastive divergence
    • G.E. Hinton Training products of experts by minimizing contrastive divergence Neural Computation 14 8 2002 1771 1800
    • (2002) Neural Computation , vol.14 , Issue.8 , pp. 1771-1800
    • Hinton, G.E.1
  • 23
    • 84885897562 scopus 로고    scopus 로고
    • Speaker independent vowel recognition using backpropagation neural network on master-slave architecture
    • J. Srinivas, G.S. Prafulla, and P. Premchand Speaker independent vowel recognition using backpropagation neural network on master-slave architecture International Journal of Computer Applications 48 3 2012 45 49
    • (2012) International Journal of Computer Applications , vol.48 , Issue.3 , pp. 45-49
    • Srinivas, J.1    Prafulla, G.S.2    Premchand, P.3
  • 24
    • 78751474732 scopus 로고    scopus 로고
    • An evaluation of multiple feed-forward networks on GPUs
    • N. Lopes, and B. Ribeiro An evaluation of multiple feed-forward networks on GPUs International Journal of Neural Systems 21 1 2011 31 47
    • (2011) International Journal of Neural Systems , vol.21 , Issue.1 , pp. 31-47
    • Lopes, N.1    Ribeiro, B.2
  • 27
    • 0004259250 scopus 로고    scopus 로고
    • Oxford University Press (Chapter C1.2 Multilayer perceptrons, pp. C1.2:1-C1.2:30)
    • L.B. Almeida Handbook of Neural Computation 1997 Oxford University Press (Chapter C1.2 Multilayer perceptrons, pp. C1.2:1-C1.2:30)
    • (1997) Handbook of Neural Computation
    • Almeida, L.B.1
  • 34
    • 69849093860 scopus 로고    scopus 로고
    • An Efficient Gradient-based Learning Algorithm Applied to Neural Networks with Selective Actuation Neurons
    • N. Lopes, and B. Ribeiro An efficient gradient-based learning algorithm applied to neural networks with selective actuation neurons Neural, Parallel and Scientific Computations 11 2003 253 272 (Pubitemid 37141689)
    • (2003) Neural Parallel and Scientific Computatiions , vol.11 , Issue.3 , pp. 253-272
    • Lopes, N.1    Ribeiro, B.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.