World Scientific
Skip main navigation
Close Drawer MenuOpen Drawer Menu

Cookies Notification

We use cookies on this site to enhance your user experience. By continuing to browse the site, you consent to the use of our cookies. Learn More
×
Our website is made possible by displaying certain online content using javascript.
In order to view the full content, please disable your ad blocker or whitelist our website www.worldscientific.com.

System Upgrade on Mon, Jun 21st, 2021 at 1am (EDT)

During this period, the E-commerce and registration of new users may not be available for up to 6 hours.
For online purchase, please visit us again. Contact us at [email protected] for any enquiries.
ArticlesNo Access

A BAYESIAN RECURRENT NEURAL NETWORK FOR UNSUPERVISED PATTERN RECOGNITION IN LARGE INCOMPLETE DATA SETS

    https://doi.org/10.1142/S0129065705000219Cited by:22
    Previous
    Next

    Abstract

    A recurrent neural network, modified to handle highly incomplete training data is described. Unsupervised pattern recognition is demonstrated in the WHO database of adverse drug reactions. Comparison is made to a well established method, AutoClass, and the performances of both methods is investigated on simulated data. The neural network method performs comparably to AutoClass in simulated data, and better than AutoClass in real world data. With its better scaling properties, the neural network is a promising tool for unsupervised pattern recognition in huge databases of incomplete observations.

    References

    • P. Chanet al., IEEE Intelligent Systems 14(6), 67 (1999), DOI: 10.1109/5254.809570. Crossref, ISI, Google Scholar
    • C. Silverstein, S. Brin and R. Motwani, Data mining and knowledge discovery 2, 39 (1998). Crossref, ISI, Google Scholar
    • D. J. Hand, The American Statistician 52(2), 112 (1998), DOI: 10.2307/2685468. ISI, Google Scholar
    • U. M.   Fayyad et al. (eds.) , Advances in Knowledge Discovery and Data Mining ( MIT press , Menlo Park , 1996 ) . Google Scholar
    • B. F. Pennington, Diagnosing Learning Disorders: A Neuropsychological Framework (The Guilford Press, 1991) p. 24. Google Scholar
    • R. Orreet al., Computational Statistics and Data Analysis 34(4), 473 (2000), DOI: 10.1016/S0167-9473(99)00114-0. Crossref, ISI, Google Scholar
    • W. DuMouchel and D. Pregibon, Empirical bayes screening for multi-item associations, Proc. 7th ACM SIGMOD KDD Int. Conf. on Knowledge Discovery and Data Mining (ACM Press, San Francisco, CA, 2001) pp. 67–76, DOI: 10.1145/502512.502526. Google Scholar
    • R. Orre, A. Bate and M. Lindquist, Bayesian neural networks used to find adverse drug related syndromes, Proc. of the ANNIMAB-1 Conf. (Springer, 2000) pp. 215–220. Google Scholar
    • A. Holst, The Use of a Bayesian Neural Network Model for Classification Tasks, PhD thesis, Dept. of Numerical Analysis and Computing Science, Royal Institute of Technology, Stockholm, Sweden, Sept. (1997), TRITA-NA-P9708 . Google Scholar
    • A. Bateet al., European J. Clinical Pharmacology 54, 315 (1998), DOI: 10.1007/s002280050466. Crossref, Medline, ISI, Google Scholar
    • A. Lansner and Ö. Ekeberg, Int. J. Neural Systems 1(1), 77 (1989), DOI: 10.1142/S0129065789000499. Link, ISI, Google Scholar
    • P.   Cheeseman and J.   Stutz , Advances in Knowledge Discovery and Data Mining , eds. U. M.   Fayyad et al. ( MIT Press , 1995 ) . Google Scholar
    • D. J.   Hand , H.   Mannila and P.   Smyth , Principles of Data Mining ( MIT Press , 2001 ) . Google Scholar
    • J. Hopfield, Proc. National Academy of Science, USA 81, 3088 (1984), DOI: 10.1073/pnas.81.10.3088. Crossref, Medline, ISI, Google Scholar
    • A. Lansner and Ö. Ekeberg, IEEE Trans on Pattern Analysis and Machine Intelligence 7(4), 490 (1985). Medline, ISI, Google Scholar
    • P. Cheeseman, J. Stutz, M. Self, W. Taylor, J. Goebel, K. Volk and H. Walker, Automatic classification of spectra from the infrared astronomical satellite (iras), tech. rep., NASA Reference publication 1217 (1989) . Google Scholar
    • M. Gyllenberg, T. Koski and T. Lund, Applying the EM-algorithm to classification of bacteria, Proc. Int. ICSC congress on Intelligent Systems and Applications2, eds. F. Naghdyet al. (2000) pp. 65–71. Google Scholar
    • Bayesian Learning Group, The autoclass project. http://ic-www.arc.nasa.gov/ic/projects/bayes-group/autoclass/. Accessed 16 June 2003 . Google Scholar
    • P. Cheeseman, J. Stutz and W. Taylor, AUTOCLASS C (version 3.3.3unx). [Unix manual pages] (2001) . Google Scholar
    • S. Olsson and I. R. Edwards, Side Effects of Drugs Annual 23, ed. J. Aronsson (Elsevier, 2000) pp. 524–529. Google Scholar
    • K. Parfitt (ed.), Martindale: The complete drug reference, 32th edn. (Pharmaceutical press, 1999). Google Scholar
    • M.   Dukes and J.   Aronson , Meyler's Side Effects of drugs   14 ( Elsevier , 2000 ) . Google Scholar
    • M. Bristow and D. Kohen, BMJ 307(6914), 1223 (1993). Crossref, Medline, ISI, Google Scholar
    • L. Sokoloff and R. Pavlakovic, Dysphagia 12(4), 177 (1997), DOI: 10.1007/PL00009533. Crossref, Medline, ISI, Google Scholar
    • T. Hayashiet al., Clin. Neuropharmacol. 20(1), 77 (1997), DOI: 10.1097/00002826-199702000-00009. Crossref, Medline, ISI, Google Scholar
    • T. A. T. Hugheset al., Postgrad. Med. J. 70(826), 581 (1994). Crossref, Medline, ISI, Google Scholar
    • F. Cruz, D. Thiagarajan and J. Harney, South. Med. J. 76(5), 684 (1983). Crossref, Medline, ISI, Google Scholar
    • R. A. Hanelet al., Arq. Neuropsiquiatr. 56(4), 833 (1998). Crossref, Medline, ISI, Google Scholar
    • A. Sandberg, Bayesian attractor neural network models of memory, PhD thesis, Royal Institute of Technology, Stockholm, Sweden (2003) . Google Scholar
    • A. Holst and A. Lansner, A higher order bayesian neural network for classification and diagnosis, Proc. Int. Workshop on Applications of Neural Networks to Telecommunications 2, eds. J. Alspector, R. Goodman and T. X. Brown (Lawrence Erlbaum Associates, Hillsdale, 1995) pp. 347–354. Google Scholar
    Remember to check out the Most Cited Articles!

    Check out our titles in neural networks today!