MULTIPLE NEURAL NETWORK MODELS GENERATOR WITH COMPLEXITY ESTIMATION AND SELF-ORGANIZATION ABILITIES
DOI:
https://doi.org/10.47839/ijc.4.3.358Keywords:
Artificial Neural Networks, Complexity Estimation, Self-Organization, Intelligent Decomposer, Universal Information processingAbstract
In this article we present a self-organizing hybrid modular approach that is aimed at reduction of processing task complexity by decomposition of an initially complex problem into a set of simpler sub-problems. This approach hybridizes Artificial Neural Networks based artificial intelligence and complexity estimation loops in order to reach a higher level intelligent processing capabilities. In consequence, our approach mixtures learning, complexity estimation and specialized data processing modules in order to achieve a higher level self-organizing modular intelligent information processing system. Experimental results validating the presented approach are reported and discussed.References
. Multiple Model Approaches to Modeling and Control, edited by R. Murray-Smith and T.A. Johansen, Taylor & Francis Publishers, 1997, ISBN 0-7484-0595-X.
. S. Goonatilake and S. Khebbal, “Intelligent Hybrid Systems: Issues, Classification and Future Directions”, in Intelligent Hybrid Systems, John Wiley & Sons, pp 1-20, ISBN 0 471 94242 1.
. Krogh A., Vedelsby J.: Neural Network Ensembles, Cross Validation, and Active Learning, in Adv in Neural Inf Processing Syst. 7, The MIT Press, Ed by G. Tesauro, pp 231-238, 1995.
. Sridhar D.V.,Bartlett E.B., Seagrave R.C., "An information theoretic approach for combining neural network process models", Neural Networks, Vol. 12, pp 915-926, Pergamon, Elsevier, 1999.
. Jordan M. I. and Xu L., "Convergence Results for the EM Approach to Mixture of Experts Architectures", Neural Networks, Vol. 8, N° 9, pp 1409-1431, Pergamon, Elsevier, 1995.
. Bruske J., Sommer G., Dynamic Cell Structure, Adv in Neural Inf Processing Systems 7, The MIT Press, Ed by G. Tesauro, pp 497-504, 1995.
. Sang K. K. and Niyogi P., Active learning for function approximation, in Neural Information Processing Systems 7, The MIT Press, Ed by G. Tesauro, pp 497-504.
. Madani K., Chebira A., "A Data Analysis Approach Based on a Neural Networks Data Sets Decomposition and it’s Hardware Implementation", PKDD 2000, Lyon, France, 2000.
. Jollifee I.T., "Principle Component Analysis", New York, Springer Verlag 1986.
. Chernoff, “Estimation of a multivariate density”, Annals of the Institute of Statistical Mathematics, vol. 18, pp. 179-189, 1966.
. Bhattacharya, “On a measure of divergence between two statistical populations defined by their probability distributions”, Bulletin of Calcutta Maths Society, vol. 35, pp. 99-110, 1943.
. J. Lin, “Divergence measures based on the Shannon entropy”, IEEE Transactions on Information Theory, 37(1):145-151, 1991.
. K. Matusita, “On the notion of affinity of several distributions and some of its applications”, Annals Inst. Statistical Mathematics, 19:181-192, 1967.
. E. Parzen, “On estimation of a probability density function and mode”, Annals of Math. Statistics, vol. 33, pp. 1065-1076, 1962.
. W.E. Pierson, “Using boundary methods for estimating class separability”, PhD Thesis, Dept of Elec. Eng., Ohio State Univ., 1998.
. Kohn, L. G. Nakano, and V. Mani, “A class discriminability measure based on feature space partitioning”, Pattern Recognition, 29(5):873-887, 1996.
. Singh S., “Pattern Recognition Using Information Slicing model”, 16th Internat. Conf. on Pattern Recog. (ICPR 2002), 11-15 August 2002, Quebec, Canada, IEEE Computer Society, ISBN 0-7695-1695-X, 2002.
. Fisher, “The mathematical theory of probabilities”, John Wiley, 2000.
. T. Kohonen, “Self-Organization and Associative Memory”, 2-nd Ed., Springer-Verlag, New York, 1988.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.