Abstract
Binary decision diagrams (BDD) is a compact and efficient representation of Boolean functions with extensions available for sets and finite-valued functions. The key feature of the BDD is an ability to employ internal structure (not necessary known upfront) of an object being modelled in order to provide a compact in-memory representation. In this paper we propose application of the BDD for machine learning as a tool for fast general pattern recognition. Multiple BDDs are used to capture a sets of training samples (patterns) and to estimate the similarity of a given test sample with the memorized training sets. Then, having multiple similarity estimates further analysis is done using additional layer of BDDs or common machine learning techniques. We describe training algorithms for BDDs (supervised, unsupervised and combined), an approach for constructing multi-layered networks combining BDDs with traditional artificial neurons and present experimental results for handwritten digits recognition on the MNIST dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bryant, R.E.: Symbolic boolean manipulation with ordered binary-decision diagrams. ACM Computing Surveys 24(3), 293–318 (1992)
Minato, S.I.: Techniques of bdd/zdd: Brief history and recent activity. IEICE Transactions on Information and Systems 96(7), 1419–1429 (2013)
Bugaychenko, D.: On application of multi-rooted binary decision diagrams to probabilistic model checking. In: Kuncak, V., Rybalchenko, A. (eds.) VMCAI 2012. LNCS, vol. 7148, pp. 104–118. Springer, Heidelberg (2012)
Segall, I., Tzoref-Brill, R., Farchi, E.: Using binary decision diagrams for combinatorial test design. In: Proceedings of the 2011 International Symposium on Software Testing and Analysis, ISSTA 2011, pp. 254–264. ACM, New York (2011)
Shirai, Y., Takashima, H., Tsuruma, K., Oyama, S.: Similarity joins on item set collections using zero-suppressed binary decision diagrams. In: Meng, W., Feng, L., Bressan, S., Winiwarter, W., Song, W. (eds.) DASFAA 2013, Part I. LNCS, vol. 7825, pp. 56–70. Springer, Heidelberg (2013)
Toda, T.: Hypergraph transversal computation with binary decision diagrams. In: Bonifaci, V., Demetrescu, C., Marchetti-Spaccamela, A. (eds.) SEA 2013. LNCS, vol. 7933, pp. 91–102. Springer, Heidelberg (2013)
Minato, S.I.: Data mining using binary decision diagrams. Synthesis Lectures on Digital Circuits and Systems, 1097 (2010)
Shirai, Y., Tsuruma, K., Sakurai, Y., Oyama, S., Minato, S.-i.: Incremental set recommendation based on class differences. In: Tan, P.-N., Chawla, S., Ho, C.K., Bailey, J. (eds.) PAKDD 2012, Part I. LNCS, vol. 7301, pp. 183–194. Springer, Heidelberg (2012)
LeCun, Y., Cortes, C., Burges, C.J.: The MNIST database of handwritten digits, http://yann.lecun.com/exdb/mnist/
Minato, S.I.: Zero-suppressed bdds for set manipulation in combinatorial problems. In: 30th Conference on Design Automation, pp. 272–277. IEEE (1993)
Bugaychenko, D.: BddFunctions: Multi-rooted binary decision diagrams package, http://code.google.com/p/bddfunctions
Bouckaert, R.R., Frank, E., Hall, M., Kirkby, R., Reutemann, P., Seewald, A., Scuse, D.: Weka manual for version 3-7-8 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Bugaychenko, D., Zubarevich, D. (2014). Fast Pattern Recognition and Deep Learning Using Multi-Rooted Binary Decision Diagrams. In: Perner, P. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2014. Lecture Notes in Computer Science(), vol 8556. Springer, Cham. https://doi.org/10.1007/978-3-319-08979-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-08979-9_6
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-08978-2
Online ISBN: 978-3-319-08979-9
eBook Packages: Computer ScienceComputer Science (R0)