Abstract
One of the main requirements in modelling, i.e. neural network training, is to assure good generalization of the obtained model. Hence, the latter requirement has to be built into the training mechanism either by constantly monitoring the behavior of the trained network on an independent data set during learning or by appropriately modifying the cost function. Akaike’s and Rissanen’s methods for formulating cost functions which naturally include model complexity terms are presented in Chapter 7 while the problem of generalization over an infinite ensemble of networks is presented in Chapter 8.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G. Deco, W. Finnoff and H.G. Zimmermann: Unsupervised Mutual Information Criterion for Elimination of Overtraining in Supervised Multilayer Networks. Neural Computation, 7, 86–107, 1995.
Y. Le Cun, J. Denker and S. Solla: Optimal Brain Damage. In Proceedings of the Neural Information Processing Systems, Denver, 598–605, 1990.
A. Weigend and D. Rumelhart: The Effective Dimension of the Space of Hidden Units. In Proceedings International Joint Conference on Neural Networks, Singapore, 1991.
G. Deco and J. Ebmeyer: Coarse Coding Resource-Allocating-Network. Neural Computation, 5, 105–114, 1993.
S.E. Fahlman and C. Lebiere: The Cascade Correlation Learning Architecture. In Advances in Neural Information Processing 2, D.S. Touretzky ed., Morgan Kaufmann, San Mateo, CA, 1990.
W. Finnoff and H.G. Zimmermann: Detecting Structure in Small Data Sets by Network Fitting under Complexity Constrains. In Proceedings of 2nd Ann. Workshop Computational Learning Theory and Natural Learning Systems, Berkeley, 1991.
A. Weigend, D. Rumelhart and B. Huberman: Generalization by Weight Elimination with Application to Forecasting. In Advances in Neural Information Processing 3, R. P. Lippman, J. Moody and D.S. Touretzky eds., Morgan Kaufmann, San Mateo, CA, 1991.
J. Moody and C. Darken: Fast Learning in Networks of Locally-Tuned Processing Units. Neural Computation, 1, 281–294, 1989.
V.N. Vapnik: Estimation of Dependencies Based on Empirical Data. Springer Verlag, New York, 1982.
V.N. Vapnik: Principles of Risk Minimization for Learning Theory. In Neural Information Processing Systems 4, J.E. Moody, S.J. Hanson and R.P. Lippmann eds., 831–838, Morgan Kaufmann, San Mateo, CA, 1992.
D. Pollard: Estimation of Dependencies Based on Empirical Data. Springer-Verlag, New York, 1984.
S. Hanson and L. Pratt: Comparing Biases for Minimal Network Construction with Back-Propagation. In Advances in Neural Information Processing II, D.S. Touretzky, Ed., Morgan Kaufmann, New York, 533–541, 1989.
S. Nowlan and G. Hinton: Adaptive Soft Weight Tying using Gaussian Mixtures. Neural Information Processing Systems 4, J.E. Moody, S.J. Hanson and R.P. Lippmann eds., 993–1000, Morgan Kaufmann, San Mateo, CA, 1992.
D. MacKay: Bayesian Modelling and Neural Networks. Ph.D thesis, Computation and Neural Systems, California Institute of Technology, Pasadena, CA, 1991.
J. Moody: The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems. In Neural Information Processing Systems 4, J.E. Moody, S.J. Hanson and R.P. Lippmann eds., 847–854, Morgan Kaufmann, San Mateo, CA, 1992.
J. Bridle, D. MacKay and A. Heading: Unsupervised Classifiers, Mutual Information and ‘Phantom Targets’. In Neural Information Processing Systems 4, J.E. Moody, S.J. Hanson and R.P. Lippmann eds., 1096–1101, Morgan Kaufmann, San Mateo, CA, 1992.
R. Linsker: How to Generate Ordered Maps by Maximizing the Mutual Information Between Input and Output Signals. Neural Computation, 1, 402–411, 1991.
A.N. Redlich: Redundancy Reduction as a Strategy for Unsupervised Learning. Neural Computation, 5, 289–304, 1993.
D. MacKay: A Practical Bayesian Framework for Backpropagation Networks. Neural Computation, 4, 448–472, 1992.
J. H. Friedman: Multivariate Adaptive Regression Splines. Annals of Statistics, 19, 1–141, 1991.
S. Nowlan and G. Hinton: Simplifying Neural Networks by Soft Weight-Sharing. Neural Computation, 4, 473–493.
C. Peterson and B. Soederberg: A New Method for Mapping Optimization Problems Onto Neural Networks. Int. J. Neural Syst., 1, 68, 1989.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer-Verlag New York, Inc.
About this chapter
Cite this chapter
Deco, G., Obradovic, D. (1996). Information Theory Based Regularizing Methods. In: An Information-Theoretic Approach to Neural Computing. Perspectives in Neural Computing. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-4016-7_10
Download citation
DOI: https://doi.org/10.1007/978-1-4612-4016-7_10
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4612-8469-7
Online ISBN: 978-1-4612-4016-7
eBook Packages: Springer Book Archive