Abstract
We present a Connectionist architecture called Modified Hyperspherical Classifier (MHC) based on: 1) the work of Cooper [5] [6] and Batchelor [2] [3] [4] about Hyperspherical Classifiers, 2) the RCE paradigm as described by Scofield et al. [10] and 3) some new considerations derived from the search of an efficient model to perform heterogeneous pattern processing using Hybrid training algorithms depending on the nature of the problem, the availability of the correct output during the training process and the operational state of the network. We use the term Hybrid Training to define the use of a supervised or an unsupervised strategy to train the same network; this definition differs from the presented by Hertz et al. [7] as Hybrid Learning, which refers to different learning strategies for each layer.
Preview
Unable to display preview. Download preview PDF.
References
B. Batchelor, B. Wilkins. “Adaptive Discriminant Functions”. Pattern Recognition. 1.968 IEE Conf. Publication, 42, pp 168–178.
B. Batchelor. “Learning machines for pattern recognition”. Ph.D. Dissertation, Southampton.
B. Batchelor. “Practical approach to pattern classification”. 1974. New York. Plenum Press.
P. Cooper. “The Hypersphere in pattern recognition”. 1962. Information and Control, 5, pp. 324–346.
P. Cooper. “A note on an adaptive hypersphere decision boundary”. 1.966. IEEE Transactions on Electronic Computers, pp. 948–959.
J. Hertz et al. “Introduction to the theory of Neural Computation”, Addison-Wesley, 1.991.
N. Nilsson. “Mathematical Foundations of Learning Machines”. 1.990. Morgan-Kaufmann.
J. Ortiz. “An Artificial Intelligence aproach to model-based gaslift troubleshoting”. M.S. Thesis. Texas ASM Univ. Texas. USA. 1990
J. Ramírez. “Use of Connectionist Classifiers to detect regularities in data”. 1.991. Intevep S.A. tech. report.
J. Ramírez, I. Torres. “Conclusions of the use of connectionist models as feature detectors”, Intevep S.A., 1.991. tech. report.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ramírez, J.M. (1993). MHC — An evolutive connectionist model for hybrid training. In: Mira, J., Cabestany, J., Prieto, A. (eds) New Trends in Neural Computation. IWANN 1993. Lecture Notes in Computer Science, vol 686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56798-4_151
Download citation
DOI: https://doi.org/10.1007/3-540-56798-4_151
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56798-1
Online ISBN: 978-3-540-47741-9
eBook Packages: Springer Book Archive