Abstract
Any point in the solution space of a perceptron can classify the training data correctly. Two kinds of the solution space, one in the weight space and the other in the input space, have been devised. This work illustrated the correspondence between these two spaces.
Supported by National Science Council
This is a preview of subscription content, log in via an institution to check access.
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
McCulloch, W.S., Pitts, W.: A Logical Calculus on the Ideas Immanent in the Nervous Activity. Bull. Math. Biophys. 5, 115–133 (1943)
Minsky, M., Papert, S.: Perceptrons. MIT Press, Cambridge (1969)
Liou, C.-Y., Chen, H.-T.: Self-Relaxation for Multilayer Perceptron. In: The Third Asian Fuzzy Systems AFSS 1998, Masan, Korea, June 18-21, pp. 113–117 (1998)
Liou, C.-Y., Huang, J.-C., Kuo, Y.-T.: Geometrical Perspective on Learning Behavior. Journal of Information Science and Engineering 21, 721–732 (2005)
Diamantaras, K.I., Strintzis, M.G.: Neural Classifiers Using One-Time Updating. IEEE Trans. Neural Networks 9(3), 436–447 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Huang, JC., Liou, CY. (2010). Solution Space of Perceptron. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds) Artificial Neural Networks – ICANN 2010. ICANN 2010. Lecture Notes in Computer Science, vol 6354. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15825-4_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-15825-4_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15824-7
Online ISBN: 978-3-642-15825-4
eBook Packages: Computer ScienceComputer Science (R0)