Abstract
The problem of vector field approximation arises in the wide range of fields such as motion control, computer vision and so on. This paper proposes a method for reconstructing an entire continuous vector field from a sparse set of sample data by training neural networks. In order to make approximation results possess inherent properties of vector fields and to attain reasonable approximation accuracy with computational efficiency, we include a priori knowledge on inherent properties of vector fields into the learning problem of neural networks, which we call model inclusive learning. An efficient learning algorithm of neural networks is derived. It is shown through numerical experiments that the proposed method makes it possible to reconstruct vector fields accurately and efficiently.
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
Rumelharlt, D.E., Hinton, G.E., Williams, R.J.: Learning Internal Representation by Error Backpropagation. In: Parallel Distributed Processing, vol. 1, MIT Press, Cambridge (1986)
Mussa-Ivaldi, F.A.: From basis functions to basis fields: vector field approximation from sparse data. Biological Cybernetics 67, 479–489 (1992)
Saehan, S., Iwagami, T., Kuroe, Y.: Learning Algorithm in Neural Networks Based on Adjoint Neuron Model Technical Report. of IEICE, NC 90-30, pp. 1–9 (1989)
Kuroe, Y., Nakai, Y., Mori, T.: ‘A Learning Method of Nonlinear Mappings by Neural Networks with Considering Their Derivatives. In: Proc. IJCNN, Nagoya, Japan, pp. 528–531 (1993)
Luenberger, D.G.: Introduction to Linear and Nonlinear Programming, pp. 194–197. Addison-Wesley, Reading (1973)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kuroe, Y., Kawakami, H. (2007). Vector Field Approximation by Model Inclusive Learning of Neural Networks . In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4668. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74690-4_73
Download citation
DOI: https://doi.org/10.1007/978-3-540-74690-4_73
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74689-8
Online ISBN: 978-3-540-74690-4
eBook Packages: Computer ScienceComputer Science (R0)