메뉴 건너뛰기




Volumn 3, Issue , 2015, Pages 2246-2255

Deep unsupervised learning using nonequilibrium thermodynamics

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; ITERATIVE METHODS; LEARNING SYSTEMS; PROBABILITY; THERMODYNAMICS;

EID: 84969975031     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (3949)

References (55)
  • 5
    • 0000582521 scopus 로고
    • Statistical analysis of non-lattice data
    • Besag, J. Statistical Analysis of Non-Lattice Data. The Statistician, 24(3), 179-195, 1975.
    • (1975) The Statistician , vol.24 , Issue.3 , pp. 179-195
    • Besag, J.1
  • 17
    • 0013344078 scopus 로고    scopus 로고
    • Training products of experts by minimizing contrastive divergence
    • Hinton, G. E. Training products of experts by minimizing contrastive divergence. Neural Computation, 14(8): 1771-1800, 2002.
    • (2002) Neural Computation , vol.14 , Issue.8 , pp. 1771-1800
    • Hinton, G.E.1
  • 19
    • 22044434800 scopus 로고    scopus 로고
    • Estimation of non-normalized statistical models using score matching
    • Hyvärinen, A. Estimation of non-normalized statistical models using score matching. Journal of Machine Learning Research, 6:695-709, 2005.
    • (2005) Journal of Machine Learning Research , vol.6 , pp. 695-709
    • Hyvärinen, A.1
  • 20
    • 4244116139 scopus 로고    scopus 로고
    • Equilibrium free-energy differences from nonequilibrium measurements: A master-equation approach
    • January
    • Jarzynski, C. Equilibrium free-energy differences from nonequilibrium measurements: A master-equation approach. Physical Review E, January 1997.
    • (1997) Physical Review E
    • Jarzynski, C.1
  • 21
    • 84962400734 scopus 로고    scopus 로고
    • Equalities and inequalities: Irreversibility and the second law of thermodynamics at the nanoscale
    • Springer
    • Jarzynski, C. Equalities and inequalities: irreversibility and the second law of thermodynamics at the nanoscale. In Annu. Rev. Condens. Matter Phys. Springer, 2011.
    • (2011) Annu. Rev. Condens. Matter Phys.
    • Jarzynski, C.1
  • 23
    • 0033225865 scopus 로고    scopus 로고
    • An introduction to variational methods for graphical models
    • Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., and Saul, L. K. An introduction to variational methods for graphical models. Machine learning, 37(2): 183-233, 1999.
    • (1999) Machine Learning , vol.37 , Issue.2 , pp. 183-233
    • Jordan, M.I.1    Ghahramani, Z.2    Jaakkola, T.S.3    Saul, L.K.4
  • 27
    • 0000937122 scopus 로고
    • Sur la théorie du mouvement brownien
    • Paris
    • Langevin, P. Sur la théorie du mouvement brownien. CR Acad. Sci. Paris, 146(530-533), 1908.
    • (1908) CR Acad. Sci. , vol.146 , pp. 530-533
    • Langevin, P.1
  • 31
    • 0034981410 scopus 로고    scopus 로고
    • Occlusion models for natural images: A statistical study of a scale-invariant dead leaves model
    • Lee, A., Mumford, D., and Huang, J. Occlusion models for natural images: A statistical study of a scale-invariant dead leaves model. International Journal of Computer Vision, 2001.
    • (2001) International Journal of Computer Vision
    • Lee, A.1    Mumford, D.2    Huang, J.3
  • 32
    • 85162376415 scopus 로고    scopus 로고
    • Unifying non-maximum likelihood learning objectives with minimum KL contraction
    • Shawe-Taylor, J., Zemel, R. S., Bartlett, P., Pereira, F. C. N., and Weinberger, K. Q. (eds.)
    • Lyu, S. Unifying Non-Maximum Likelihood Learning Objectives with Minimum KL Contraction. In Shawe-Taylor, J., Zemel, R. S., Bartlett, P., Pereira, F. C. N., and Weinberger, K. Q. (eds.), Advances in Neural Information Processing Systems 24, pp. 64-72. 2011.
    • (2011) Advances in Neural Information Processing Systems , vol.24 , pp. 64-72
    • Lyu, S.1
  • 35
    • 0000273048 scopus 로고    scopus 로고
    • Annealed importance sampling
    • January
    • Neal, R. Annealed importance sampling. Statistics and Computing, January 2001.
    • (2001) Statistics and Computing
    • Neal, R.1
  • 40
    • 0040422903 scopus 로고
    • Learning factorial codes by predictability minimization
    • Schmidhuber, J. Learning factorial codes by predictability minimization. Neural Computation, 1992.
    • (1992) Neural Computation
    • Schmidhuber, J.1
  • 42
    • 81855161540 scopus 로고    scopus 로고
    • New method for parameter estimation in probabilistic models: Minimum probability flow
    • November
    • Sohl-Dickstein, J., Battaglino, P., and De Weese, M. New Method for Parameter Estimation in Probabilistic Models: Minimum Probability Flow. Physical Review Letters, 107(22): 11-14, November 2011a. ISSN 0031-9007. doi: 10.1103/Phys Rev Lett. 107.220601.
    • (2011) Physical Review Letters , vol.107 , Issue.22 , pp. 11-14
    • Sohl-Dickstein, J.1    Battaglino, P.2    De Weese, M.3
  • 48
    • 0001051762 scopus 로고
    • Condition of the TAP equation for the infinite-ranged Ising spin glass model
    • T, P. Convergence condition of the TAP equation for the infinite-ranged Ising spin glass model. J. Phys. A: Math. Gen. 15 1971, 1982.
    • (1982) J. Phys. A: Math. Gen. , vol.15 , pp. 1971
    • Convergence, T.P.1
  • 49
    • 0001143296 scopus 로고    scopus 로고
    • Mean-field theory of Boltzmann machine learning
    • January
    • Tanaka, T. Mean-field theory of Boltzmann machine learning. Physical Review Letters E, January 1998.
    • (1998) Physical Review Letters E
    • Tanaka, T.1
  • 50
    • 84864448320 scopus 로고    scopus 로고
    • Mixtures of conditional Gaussian scale mixtures applied to multiscale image representations
    • Theis, L., Hosseini, R., and Bethge, M. Mixtures of conditional Gaussian scale mixtures applied to multiscale image representations. PloS one, 7(7):e39857, 2012.
    • (2012) PloS One , vol.7 , Issue.7 , pp. e39857
    • Theis, L.1    Hosseini, R.2    Bethge, M.3
  • 54
    • 84862289622 scopus 로고    scopus 로고
    • A new learning algorithm for mean field Boltzmann machines
    • January
    • Welling, M. and Hinton, G. A new learning algorithm for mean field Boltzmann machines. Lecture Notes in Computer Science, January 2002.
    • (2002) Lecture Notes in Computer Science
    • Welling, M.1    Hinton, G.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.