Abstract
Like humans, artificial neural networks can learn from examples. In supervised learning, an example consists of a “question” and its “answer.” The answer is provided by a “teacher” and used by the “student” to update her2 internal representation, i.e. the values of her neural weights. Using techniques from statistical mechanics, many properties arising from such a simple scheme have been investigated. The one-layered perceptron is a popular platform for these studies: it is complicated enough to arrive at interesting results, yet simple enough to be described analytically. Excellent reviews of the main achievements can be found in Seung et al. (1992), and Watkin et al. (1993).
In this paper, we will sometimes use rather colloquial language, hoping that this helps to elucidate some of the concepts. We sincerely apologize to any readers as males. This is definitely not an example of traditional role modeling, for in the end we will see how a smart female student outperforms her male teacher.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Anlauf, J., & M. Biehl (1989). AdaTron: An adaptive perceptron algorithm. Euro-physics Letters 10 687–692.
Biehl, M., & H. Schwarze (1993). Learning drifting concepts with neural networks. Journal of Physics A 26 2651–2665.
Duda, R., & P. Hart (1973). Pattern classification and scene analysis. New York: Wiley.
Frean, M. (1992). A “thermal” perceptron learning rule. Neural Computation 4 946–957.
Gardner, E. (1988). The space of interactions in neural network models. Journal of Physics A 21 257–270.
Heskes, T., & B. Kappen (1992). Learning-parameter adjustment in neural networks. Physical Review A 45 8885–8893.
Heskes, T. (1994). On Fokker-Planck approximations of on-line learning processes. Journal of Physics A 27 5145–5160.
Kampen van, N. (1992). Stochastic processes in physics and chemistry Amsterdam: North-Holland.
Kinouchi, O., & N. Caticha (1992). Optimal generalization in perceptrons. Journal of Physics A 25 6243–6250.
Kinouchi, O., & N. Caticha (1993). Lower bounds on generalization errors for drifting rules. Journal of Physics A 26 6161–6171.
Kinzel, W., & P. Rujan (1990). Improving a network generalization ability by selecting examples. Europhysics Letters 13 473–477.
Opper, M., W. Kinzel, J. Kleinz, & R. Nehl (1990). On the ability of the optimal perceptron to generalise. Journal of Physics A 23L581–L586.
Opper, M., & D. Haussler (1991). Calculation of the learning curve of Bayes optimal classification algorithm for learning a perceptron with noise. Proceedings of the 4th Annual Workshop on Computational Learning Theory (pp. 75–87). San Mateo, CA: Morgan Kauffman.
Pitrat, J. (1991). An intelligent system must and can observe its own behavior. In T. Kohonen & F. Fogelman-Soulié (eds.), Cognitiva 90. At the crossroads of artificial intelligence, cognitive science, and Neuroscience (pp. 199–128). Amsterdam: North-Holland.
Rosenblatt, F. (1962). Principles of neurodynamics. New York: Spartan.
Seung, H., H. Sompolinsky, & N. Tishby (1992). Statistical mechanics of learning from examples. Physical Review A 45 6056–6091.
Watkin, T., A. Rau, & M. Biehl (1993). The statistical mechanics of learning a rule. Reviews of Modern Physics 65 499–556.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Heskes, T. (2000). The Use of Being Stubborn and Introspective. In: Cruse, H., Dean, J., Ritter, H. (eds) Prerational Intelligence: Adaptive Behavior and Intelligent Systems Without Symbols and Logic, Volume 1, Volume 2 Prerational Intelligence: Interdisciplinary Perspectives on the Behavior of Natural and Artificial Systems, Volume 3. Studies in Cognitive Systems, vol 26. Springer, Dordrecht. https://doi.org/10.1007/978-94-010-0870-9_75
Download citation
DOI: https://doi.org/10.1007/978-94-010-0870-9_75
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-3792-1
Online ISBN: 978-94-010-0870-9
eBook Packages: Springer Book Archive