Abstract
TAM (Topographic Attentive Mapping) network is a biologically-motivated neural network. In this paper, we define the Gabor function type receptive field and incorporate it to the TAM network’s feature layer. We also discuss the orientation selectivity of the receptive field through some examples of character recognition.
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
S. Marčelja (1980) Optical Society of America 70,11:1297–1300
J. Daugman (1985) Optical Society of America 2,7:1160–1169
S. Grossberg (1999) Spatial Vision 12,2:163–185
K. Fukushima (2001) Biological Cybernetics 84,4:251–259
J.R. Williamson (2001) Neural Computation 13:563–593
I. Hayashi and H. Maeda (2003) Proceedings of the 4th International Symposium on Advanced Intelligent Systems(ISIS2003) 620–623
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hayashi, I., Williamson, J.R. (2006). A Study of Orientation Selectivity of TAM Network Incorporated Receptive Field Structure. In: Murase, K., Sekiyama, K., Naniwa, T., Kubota, N., Sitte, J. (eds) Proceedings of the 3rd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE 2005). Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-29344-2_28
Download citation
DOI: https://doi.org/10.1007/3-540-29344-2_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28496-3
Online ISBN: 978-3-540-29344-6
eBook Packages: EngineeringEngineering (R0)