메뉴 건너뛰기




Volumn , Issue , 2011, Pages

Expressive power and approximation errors of Restricted Boltzmann Machines

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION ERRORS; CLASS OF DISTRIBUTIONS; DIFFERENT CLASS; EXPRESSIVE POWER; HIDDEN UNITS; KULLBACK LEIBLER DIVERGENCE; MACHINE MODELLING; POWER ERRORS; PROBABILITY: DISTRIBUTIONS; RESTRICTED BOLTZMANN MACHINE;

EID: 85162368944     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (52)

References (26)
  • 1
    • 33846165056 scopus 로고    scopus 로고
    • Maximizing multi-information
    • N. Ay and A. Knauf. Maximizing multi-information. Kybernetika, 42:517-538, 2006.
    • (2006) Kybernetika , vol.42 , pp. 517-538
    • Ay, N.1    Knauf, A.2
  • 3
    • 0038289925 scopus 로고    scopus 로고
    • Dynamical properties of strongly interacting Markov chains
    • N. Ay and T. Wennekers. Dynamical properties of strongly interacting Markov chains. Neural Networks, 16:1483-1497, 2003.
    • (2003) Neural Networks , vol.16 , pp. 1483-1497
    • Ay, N.1    Wennekers, T.2
  • 5
    • 0003369433 scopus 로고
    • Fundamentals of statistical exponential families: With applications in statistical decision theory
    • Hayworth, CA, USA
    • L. Brown. Fundamentals of Statistical Exponential Families: With Applications in Statistical Decision Theory. Inst. Math. Statist., Hayworth, CA, USA, 1986.
    • (1986) Inst. Math. Statist.
    • Brown, L.1
  • 9
    • 0001740680 scopus 로고
    • Finite exchangeable sequences
    • P. Diaconis and D. Freedman. Finite exchangeable sequences. Ann. Probab., 8:745-764, 1980.
    • (1980) Ann. Probab. , vol.8 , pp. 745-764
    • Diaconis, P.1    Freedman, D.2
  • 10
    • 0345368881 scopus 로고
    • Unsupervised learning of distributions on binary vectors using 2-layer networks
    • Y. Freund and D. Haussler. Unsupervised learning of distributions on binary vectors using 2-layer networks. NIPS, pages 912-919, 1992.
    • (1992) NIPS , pp. 912-919
    • Freund, Y.1    Haussler, D.2
  • 11
    • 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 Comput., 14:1771-1800, 2002.
    • (2002) Neural Comput. , vol.14 , pp. 1771-1800
    • Hinton, G.E.1
  • 13
    • 33745805403 scopus 로고    scopus 로고
    • A fast learning algorithm for Deep Belief Nets
    • G. E. Hinton, S. Osindero, and Y. Teh. A fast learning algorithm for Deep Belief Nets. Neural Comput., 18:1527-1554, 2006.
    • (2006) Neural Comput. , vol.18 , pp. 1527-1554
    • Hinton, G.E.1    Osindero, S.2    Teh, Y.3
  • 14
    • 0001927585 scopus 로고
    • On information and sufficiency
    • S. Kullback and R. Leibler. On information and sufficiency. Ann. Math. Stat., 22:79-86, 1951.
    • (1951) Ann. Math. Stat. , vol.22 , pp. 79-86
    • Kullback, S.1    Leibler, R.2
  • 15
    • 45749110924 scopus 로고    scopus 로고
    • Representational power of Restricted Boltzmann Machines and Deep Belief Networks
    • N. Le Roux and Y. Bengio. Representational power of Restricted Boltzmann Machines and Deep Belief Networks. Neural Comput., 20(6):1631-1649, 2008.
    • (2008) Neural Comput. , vol.20 , Issue.6 , pp. 1631-1649
    • Le Roux, N.1    Bengio, Y.2
  • 16
    • 77955997114 scopus 로고    scopus 로고
    • Deep Belief Networks are compact universal approximators
    • N. Le Roux and Y. Bengio. Deep Belief Networks are compact universal approximators. Neural Comput., 22:2192-2207, 2010.
    • (2010) Neural Comput. , vol.22 , pp. 2192-2207
    • Le Roux, N.1    Bengio, Y.2
  • 17
    • 0003286354 scopus 로고
    • Mixture models: Theory, geometry, and applications
    • B. Lindsay. Mixture models: theory, geometry, and applications. Inst. Math. Statist., 1995.
    • (1995) Inst. Math. Statist.
    • Lindsay, B.1
  • 18
    • 77956527887 scopus 로고    scopus 로고
    • Restricted Boltzmann Machines are hard to approximately evaluate or simulate
    • P. M. Long and R. A. Servedio. Restricted Boltzmann Machines are hard to approximately evaluate or simulate. In Proceedings of the 27-th ICML, pages 703-710, 2010.
    • (2010) Proceedings of the 27-th ICML , pp. 703-710
    • Long, P.M.1    Servedio, R.A.2
  • 21
    • 79958248389 scopus 로고    scopus 로고
    • Refinements of universal approximation results for deep belief networks and restricted boltzmann machines
    • G. Montúfar and N. Ay. Refinements of universal approximation results for Deep Belief Networks and Restricted Boltzmann Machines. Neural Comput., 23(5):1306-1319, 2011.
    • (2011) Neural Comput. , vol.23 , Issue.5 , pp. 1306-1319
    • Montúfar, G.1    Ay, N.2
  • 23
    • 79954417995 scopus 로고    scopus 로고
    • Support sets of exponential families and oriented matroids
    • J. Rauh, T. Kahle, and N. Ay. Support sets of exponential families and oriented matroids. Int. J. Approx. Reason., 52(5):613-626, 2011.
    • (2011) Int. J. Approx. Reason. , vol.52 , Issue.5 , pp. 613-626
    • Rauh, J.1    Kahle, T.2    Ay, N.3
  • 26
    • 77955729257 scopus 로고    scopus 로고
    • Higher coordination with less control - A result of infromation maximization in the sensori-motor loop
    • K. G. Zahedi, N. Ay, and R. Der. Higher coordination with less control - a result of infromation maximization in the sensori-motor loop. Adaptive Behavior, 18(3-4):338-355, 2010.
    • (2010) Adaptive Behavior , vol.18 , Issue.3-4 , pp. 338-355
    • Zahedi, K.G.1    Ay, N.2    Der, R.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.