Abstract
In this paper, we focus on the concept classes \({\mathcal {C}}_{{\mathcal{N}}}\) induced by Bayesian networks. The relationship between two-dimensional values induced by these concept classes is studied, one of which is the VC-dimension of the concept class \({\mathcal {C}}_{\cal {N}},\) denoted as \(VCdim({\mathcal {N}}), \) and other is the smallest dimensional of Euclidean spaces into which \({\mathcal {C}}_{{\mathcal {N}}}\) can be embedded, denoted as \(Edim({\mathcal {N}}). \) As a main result, we show that the two-dimensional values are equal for the Bayesian networks with n ≤ 4 variables, called the VE-dimension for that Bayesian networks.
Similar content being viewed by others
References
Jansen R, Yu H, Greenbaum D et al (2003) A Bayesian networks approach for predicting protein–protein interactions from genomic data. Sci Agric 302(5644):449–453
Cobb BR, Shenoy PP (2006) Operation for inference in continuous Bayesian networks with linear deterministic variables. Int J Approx Reason 4(1-2):21–36
Yimin Huang, Marco Valtorta (2008) On the completeness of an identifiability algorithm for semi-Markovian models. Ann Math Artif Intell 54:363–408
Aritz P, Pedro L, Inaki I (2009) Bayesian classifiers based on kernel density estimation: flexible classifiers. Int J Approx Reason 50(7):341–362
Coup VMH, van der Gaag LC (2002) Properties of sensitivity analysis of Bayesian belief networks. Ann Math Artif Intell 36:323–356
Franc V, Savchynskyy B (2008) Discriminative Learning of Max-Sum classifiers. J Mach Learn Res 9:67–104
Pernkopf F (2004) Detection of surface defects on raw steel blocks using Bayesian network classifiers. Pattern Anal Appl 4:333–342
Lafferty J, Lebanon G (2005) Diffusion kernels on statistical manifolds. J Mach Learn Res 6:129–163
Tsuda K, Akaho S, Kawanabe M, Muller K (2004) Asymptotic properties of the Fisher kernel. Neural Comput Appl 16:115–137
Pahikkala T, Tsivtsivadze E, Airola A, Jarvinen J, Boberg J (2009) An efficient algorithm for learning to rank from preference graphs. Mach Learn 75:129–165
Ben-David S, Eiron N, Simon HU (2002) Limitations of learning via embeddings in Euclidean half-spaces. J Mach Learn Res 3:441–461
Chechik G, Heitz G, Galel GE, Koller D (2008) Max-margin classification of data with absent features. J Mach Learn Res 9:1–21
Altun Y., Tsochantaridis I., Hofmann T. (2003) Hidden Markov support vector machines. In: Proceedings of the 20th International conference on machine learning. AAAI Press, Menlo Park, pp 3–10
Nakamura A, Schmitt M, Schmitt N, Simon HU (2005) Inner product space of Bayesian networks. J Mach Learn Res 6:1383–1403
Jaime S (2011) Cardoso and Ricardo Sousa, measuring the performance of ordinal classification. Int J Pattern Recognit Artif Intell 25(8):1173–1195
Youlong Y, Yan W (2009) VC dimension and inner product space induced by Bayesian networks. Int J Approx Reason 50(7):1036–1045
Youlong Y, Yan W (2009) Inner product space and concept classes induced by Bayesian networks. Acta Appl Math 106(3):337–348
Chickering DM (1995) A transformational characterization of Bayesian network structures. In: Hanks S, Besnard P (eds) Proceeding of the Eleventh conference on uncertainty in artifical intelligence. Morgan Kaufmann, Burlington, pp 87–98
Chickering DM (2002) Learing equivalence classes of Bayesian-network structures. J Mach Learn Res 2:445–498
Youlong Y, Yan W (2012) On the properties of concept classes induced by some multiple-valued Bayesian networks. Inf Sci 184:155–165
Verma T, Pearl J (1990) Causal networks: semantics and expressiveness. In: Shachter RD, Levitt TS, Kanal LN, Lemmer JF (eds) Uncertainty in artificial intelligence. Proceedings of the Sixth Conference, North Holland, Amsterdam
Anthony M, Bartlett PL (1999) Learning in neural networks: theoretical foundations. Cambridge University Press, Cambridge, pp 73–83; 108–122
Acknowledgments
This work was supported by National Natural Science Foundation of China (61075055). We would like to thank the anonymous reviewers for their valuable comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yang, Y., Wu, Y. VE dimension induced by Bayesian networks over the boolean domain. Pattern Anal Applic 17, 799–807 (2014). https://doi.org/10.1007/s10044-013-0320-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-013-0320-3