Abstract
We study the dynamics of learning in a hierarchical model such as multilayer perceptron. Such a model includes singularities, which affects its dynamics seriously. The Milnor type attractors appear, because of the singularity. We will show its trajectories explicitly, and present the topological nature of the singularities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cousseau, F., Ozeki, T., Amari, S.: Dynamics of learning in multilayer perceptrons near singularities. IEEE. Trans. Neural. Netw. 19 (2008) 1313–1328.
Amari, S.: Natural gradient works efficiently in learning. Neural. Comput. 10 (1998) 251–276.
Amari, S., Park, H., Ozeki, T.: Singularities affect dynamics of learning in neuromanifolds. Neural. Comput. 18 (2006) 1007–1065.
Fukumizu, K., Amari, S.: Local minima and plateaus in hierarchical structures of multilayer perceptrons. Neural. Netw. 13 (2000) 317–327.
Wei, H., Zhang, J., Cousseau, F., Ozeki, T., Amari, S.: Dynamics of learning near singularities in layered networks. Neural. Comput. 20 (2008) 813–843.
Wei, H., Amari, S.: Dynamics of learning near singularities in radial basis function networks. Neural. Netw. 21 (2008) 989–1005.
Milnor, J.: On the Concept of Attractor. Commun. Math. Phys. 99 (1985) 177–195.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media B.V.
About this paper
Cite this paper
Amari, Si., Ozeki, T., Cousseau, F., Wei, H. (2011). Dynamics of Learning In Hierarchical Models – Singularity and Milnor Attractor. In: Wang, R., Gu, F. (eds) Advances in Cognitive Neurodynamics (II). Springer, Dordrecht. https://doi.org/10.1007/978-90-481-9695-1_1
Download citation
DOI: https://doi.org/10.1007/978-90-481-9695-1_1
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-9694-4
Online ISBN: 978-90-481-9695-1
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)