Abstract
Hierarchical systems of neural networks based on the backpropagation algorithm were used to test the hypothesis that rare categories could be learned more accurately and in shorter training times than in nonhierarchical neural networks also based on the backpropagation algorithm. In two artificial data sets, the problem of learning rare categories was quantified and an existing solution was shown to be inadequate. HNNs were compared to nonhierarchical neural networks. In both artificial examples, HNNs performed better than nonhierarchical neural networks in terms of sensitivity and time to train. Specificities were not significantly different. In two real-world examples, these results were confirmed.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Rumelhart DE; Hinton GE; Williams RJ. Learning internal representation by error propagation. In Rumelhart, D.E., and McClelland, J.L. (eds) Parallel Distributed Processing. MIT Press, Cambridge, 1986.
Hertz JA; Palmer RG; Krogh, AS. Introduction to the Theory of Neural Computation. Addison-Wesley, Redwood City, 1991.
Gray NAB. Constraints on “learning machine” classification methods. Analytical Chemistry, 1976, 48(14):2265–8.
Ohno-Machado L. Identification of Low Frequency Patterns in Backpropagation Neural Networks. JAMIA Symposium Supplement, 1994, 853–9.
Ohno-Machado L; Walker MG; Musen MA. Hierarchical Neural Networks for Survival Analysis. Proceedings of the MEDINFO, 1995.
Sunil EVT; Shin YC; Kumara SRT. Machining Conditioning Monitoring via Neural networks. ASME Winter Annual Meeting, in Monitoring and Control of Manufacturing Processes. SY Liang and TC Tsao (Co-eds), PED-VOL 44, ASME Publications, pp85–95, December 1990
Jordan RA; Nowlan SJ; Hinton SJ. Adaptive mixtures of local experts. Neural Computation, 1991, 3:79–87.
Curry B; Rumelhart DE. MSnet: A neural network that classifies mass spectra. Tetrahedron Computer Methodology, 1990, 3:213–37.
Shepard RN. Multidimensional scaling, tree-fitting, and clustering. Science, 1980, 210:390–8.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ohno-Machado, L., Musen, M.A. (1995). Learning rare categories in backpropagation. In: Wainer, J., Carvalho, A. (eds) Advances in Artificial Intelligence. SBIA 1995. Lecture Notes in Computer Science, vol 991. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0034813
Download citation
DOI: https://doi.org/10.1007/BFb0034813
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60436-5
Online ISBN: 978-3-540-47467-8
eBook Packages: Springer Book Archive