On the relationship between deterministic and probabilistic directed Graphical models: From Bayesian networks to recursive neural networks

Neural Networks

Volumn 18, Issue 8, 2005, Pages 1080-1086

  Baldi, Pierre ^a,b   Rosen Zvi, Michal ^c  

^a 5226 Donald Bren Hall   (United States)

^b UNIVERSITY OF CALIFORNIA   (United States)

^c HEBREW UNIVERSITY OF JERUSALEM   (Israel)

Author keywords

Bayesian networks; Belief propagation; Constraint networks; Graphical models; Recurrent neural networks; Recursive neural networks

Indexed keywords

ALGORITHMS; CONSTRAINT THEORY; FUNCTIONS; GRAPH THEORY; LEARNING SYSTEMS; MATHEMATICAL MODELS; PROBABILITY DISTRIBUTIONS;

BAYESIAN NETWORKS; BELIEF PROPAGATION; CONSTRAINT NETWORKS; GRAPHICAL MODELS; RECURSIVE NEURAL NETWORKS;

RECURRENT NEURAL NETWORKS;

ALGORITHM; ARCHITECTURE; ARTICLE; ARTIFICIAL NEURAL NETWORK; BAYES THEOREM; COMPUTER MODEL; CORRELATION ANALYSIS; COVARIANCE; PARAMETER; PRIORITY JOURNAL; PROCESS DESIGN; STATISTICAL DISTRIBUTION; SYSTEM ANALYSIS;

BAYES THEOREM; COMPUTER GRAPHICS; COMPUTER SIMULATION; HUMANS; MODELS, STATISTICAL; NEURAL NETWORKS (COMPUTER); SIGNAL PROCESSING, COMPUTER-ASSISTED;

EID: 26944481531     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2005.07.007     Document Type: Article

References (16)

1. P. Baldi, and Y. Chauvin Hybrid modeling, HMM/NN architectures, and protein applications Neural Computation 8 7 1996 1541 1565
2. P. Baldi, and G. Pollastri The principled design of large-scale recursive neural network architectures - DAG-RNNs and the protein structure prediction problem Journal of Machine Learn/my Research 4 2003 575 602
3. Baldi, P., Rosen-Zvi, M. (2005). On the relationship between deterministic and probabilistic directed graphical models: From Bayesian networks to recursive neural networks and back. Technical report, Irvine: Department of Computer Science, University of California.
4. Barber, D. (2000). Dynamic Bayesian networks with determinsitic latent tables. In Advances in neural information processing systems (Vol. 12).
5. P. Billingsley Probability and measure 3rd ed. 1995 Wiley NY
6. B. Bozhena, R. Dechter. The epsilon-cutset effect in bayesian networks. Technical report, School of Information and Computer Science, University of California, Irvine, 2001
7. R. Dechter Constraint processing 2003 Morgan Kauffman
8. P. Frasconi, M. Gori, and A. Sperduti A general framework for adaptive processing of data structures IEEE Transactions on Neural Networks 9 5 1998 768 786
9. C. Goller, and A. Kuchler Learning task-dependent distributed structure-representations by backpropagation through structure IEEE International Conference on Neural Networks 1996 347 352
10. D. Heckerman M.I. Jordan A tutorial on learning with Bayesian networks Learning in graphical models 1998 Kluwer Dordrecht
11. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner Gradient-based learning applied to document recognition Proceedings of the IEEE 86 11 1998 2278 2324
12. A. Micheli, A. Sperduti, A. Starita, and A.M. Bianucci Analysis of the internal representations developed by neural networks for structures applied to quantitative structure-activity relationship studies of benzodiazepines Journal of Chemical Information and Computer Sciences 41 2001 202 218
13. J. Pearl Fusion, propagation, and structuring in belief networks Artificial Intelligence 29 3 1986 241 288
14. J. Pearl Probabilistic reasoning in intelligent systems: Networks of plausible inference 1988 Morgan Kaufmann San Mateo, CA
15. M. Rosen-Zvi, M. I. Jordan. Approximate inference and the DLR equations. Technical report. Computer Science Division, University of California, Berkeley, 2003.
16. A. Sperduti, and A. Starita Supervised neural networks for the classification of structures IEEE Transactions on Neural Networks 8 3 1997 714 735