Relating Bayesian learning to training in recurrent networks

被引:0
|
作者
Spiegel, R [1 ]
机构
[1] Univ London Goldsmiths Coll, Dept Comp, London SE14 6NW, England
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
It will be demonstrated that a recurrent neural network relying on an error correcting (truncated gradient descent) learning algorithm and a localist coding scheme is able to converge to,a solution that would be expected from Bayesian learning. This is possible even without implementing Bayes theorem and without assigning prior probabilities to the model.
引用
收藏
页码:908 / 913
页数:6
相关论文
共 50 条
  • [1] Bayesian learning for recurrent neural networks
    Crucianu, M
    Boné, R
    de Beauville, JPA
    [J]. NEUROCOMPUTING, 2001, 36 (01) : 235 - 242
  • [2] Nonlinear Bayesian Filters for Training Recurrent Neural Networks
    Arasaratnam, Ienkaran
    Haykin, Simon
    [J]. MICAI 2008: ADVANCES IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2008, 5317 : 12 - 33
  • [3] Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
    Gan, Zhe
    Li, Chunyuan
    Chen, Changyou
    Pu, Yunchen
    Su, Qinliang
    Carin, Lawrence
    [J]. PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1, 2017, : 321 - 331
  • [4] Recursive Bayesian Levenberg-Marquardt training of recurrent neural networks
    Mirikitani, Derrick
    Nikolaev, Nikolay
    [J]. 2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, 2007, : 282 - 287
  • [5] Constrained Training of Recurrent Neural Networks for Automata Learning
    Aichernig, Bernhard K.
    Koenig, Sandra
    Mateis, Cristinel
    Pferscher, Andrea
    Schmidt, Dominik
    Tappler, Martin
    [J]. SOFTWARE ENGINEERING AND FORMAL METHODS, SEFM 2022, 2022, 13550 : 155 - 172
  • [6] Toward Training Recurrent Neural Networks for Lifelong Learning
    Sodhani, Shagun
    Chandar, Sarath
    Bengio, Yoshua
    [J]. NEURAL COMPUTATION, 2020, 32 (01) : 1 - 35
  • [7] A LEARNING AUTOMATA-BASED TECHNIQUE FOR TRAINING BAYESIAN NETWORKS
    Rezvani, Nabi Allah
    Meybodi, Mohammad Reza
    [J]. PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER THEORY AND ENGINEERING (ICACTE 2009), VOLS 1 AND 2, 2009, : 201 - 212
  • [8] A genetic algorithm for learning Bayesian Networks to match training sets
    Ling, YB
    Jiang, YF
    Wu, XJ
    [J]. Proceedings of the 8th Joint Conference on Information Sciences, Vols 1-3, 2005, : 1489 - 1492
  • [9] Recurrent Neural Networks Training Using Derivative Free Nonlinear Bayesian Filters
    Todorovic, Branimir
    Stankovic, Miomir
    Moraga, Claudio
    [J]. COMPUTATIONAL INTELLIGENCE, IJCCI 2014, 2016, 620 : 383 - 410
  • [10] Rates of learning in gradient and genetic training of recurrent neural networks
    Riaza, R
    Zufiria, PJ
    [J]. ARTIFICIAL NEURAL NETS AND GENETIC ALGORITHMS, 1999, : 95 - 99