Abstract
Systems capable of recognizing and learning two-dimensional patterns can be used in imaging systems and robotic perception systems. The symbolic and neuromorphic methods for pattern processing problems of this type are complementary in character. We present a hybrid system that utilizes components of symbolic and neuromorphic type; we employ two hybrid components that simultaneously operate up on the same data to produce hypotheses about the data. To resolve the potential conflicts in these hypotheses, we propose a method that learns a combination rule based on a set of examples. We employ the method of empirical risk minimization that does not require knowledge about the error probability distributions of the modules. We are building a prototype system to recognize control panels using a vision system.
Partally funded by Virginia's Center for Innovative Technology under grant #INF-90-015, the Department of Energy through Oak Ridge National Laboratory operated by Martin Marietta Energy Systems, Inc., under the contract #19X-SE043V, and by Old Dominion University Summer Faculty Fellowship for 1991.
Preview
Unable to display preview. Download preview PDF.
References
J. Amsterdam, Extending the Valiant learning model, Proc. of 5th Int. Conf. on Machine Learning, June 12–14, 1988, pp. 381–394.
A. Blumer, A. Ehrenfeucht, D. Haussler, and M.K. Warmuth, Learnability and the Vapnik-Chervonenkis dimension, J. Assoc. Comput. Mach., vol 36, no.4, 1989, pp. 929–965.
R.S. Boyer, and J.S. Moore, A fast string searching algorithm, Communications of ACM, vol. 20, 1977, pp. 762–772.
H. Bunke, H., Hybrid Approaches, in Syntactic and Structural Pattern Recognition, Edited by G. Ferrate, T. Pavlidis, A. Sanfeliu, H. Bunke, NATO ASI Series, Series F: Computer and System Sciences Vol. 45, Springer-Verlag, 1988, pp. 335–361. Also private communication in June 1990.
R.E. Duda, and P.E. Hart, Pattern Classification and Scene Analysis, Wiley, New York, 1973.
H.F. Durrant-Whyte, Consistent integration and propagation of disparate sensor observations, Int. J. Robot. Res., vol. 6, no.3, 1987, pp. 3–24.
C.W. Glover, M. Silliman, M. Walker, P. Spelt, N.S.V. Rao, Hybrid neural network and rule-based pattern recognition system capable of self-modification, Proc. SPIE Conf. on Applications of Artificial Intelligence, vol. VIII, ed. M. Trivedi, 1990.
D. Haussler, Generalizing the PAC model: sample size bounds from metric dimension-based uniform convergence results, Proc. 3rd Symp. Found. Comput. Sci., 1989, pp. 40–45.
D.S. Hirschberg, A linear space algorithm for computing maximal common subsequences, Commun. ACM, vol. 18, no. 6, 1975, 341–343.
A. Kak and S. Chen (eds.), Spatial Reasoning and Multi-Sensor Fusion, Morgan Kaufman Pub. Inc., 1987.
D.E. Knuth, J.H. Marris and V.R. Pratt, Fast pattern matching in strings, SIAM J. Computing, vol. 6, 1977, pp. 323–250.
G.M. Landau and U. Vishkin, Fast parallel and serial approximate string matching, J. Algorithms, vol. 10, 1989, pp. 157–169.
R.C. Luo and M.G. Kay, Multisensor integration and fusion in intelligent systems, IEEE Trans. Syst. Man Cybernetics, vol. 19, no. 5, 1989, pp. 901–931.
.L. Minsky and S. A. Papert, Perceptrons, expanded edition, MU Press, 1988.
B.K. Natarajan, On learning sets and functions, Machine Learning, vol.4, 1989, pp. 67–97.
Y. Pao, Adaptive Pattern Recognition and Neural Networks, Addison-Wesley Pub. Co., 1989.
N.S.V. Rao and C.W. Glover, Computational aspects of similarity measures based on linearizations of lattice points, Proc. IAPR Workshop on Syntactic and Structural Pattern Recognition, Murray Hill, New Jersey, June 13–15, 1990, pp. 351–365.
N.S.V. Rao and C.W. Glover, Hybrid intelligent perception system, Proc. Southeastcon'91, Williamsburg, Virginia, 1991, pp. 832–836.
N.S.V. Rao, E.M. Oblow and C.W. Glover, N-Learners problem III: Fusion of concepts, Tech. Rep., Department of Computer Science, Old Dominion University, 1991, under preparation.
A. R. Reibman and L.W. Nolte, Optimal detection and performance of distributed sensor systems, IEEE Trans. Aerospace Electronic Syst., vol. AES-23, no.1, 1987, pp. 24–30.
D.E. Rumelhart et al, Parallel Distributed Processing, Vol.1, MIT Press, 1986.
M.R. Teague, Image analysis via the general theory of moments, J. Opt. Soc. Am., vol. 70, 1987, pp. 920–930.
L.G. Valiant, A Theory of the learnable, Communications of the ACM, vol. 27, 1984, pp. 1134–1142.
V.N. Vapnik, Estimation of Dependences Based on Empirical Data, Springer-Verlag, New York, 1982.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Glover, C.W., Oblow, E.M., Rao, N.S.V. (1991). Hybrid pattern recognition system capable of self-modification. In: Ras, Z.W., Zemankova, M. (eds) Methodologies for Intelligent Systems. ISMIS 1991. Lecture Notes in Computer Science, vol 542. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-54563-8_97
Download citation
DOI: https://doi.org/10.1007/3-540-54563-8_97
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54563-7
Online ISBN: 978-3-540-38466-3
eBook Packages: Springer Book Archive