Abstract
In previous work[1] it was shown that a mechanism competing for a presynaptic factor enables the self-organizing formation of local receptive fields with orientation selectivity, even though the synapses between the input and output layers are all nonlocal, i.e., fully connected. The previous model, however, assumed a priori competitive systems, called hypercolumns, that may not appropriately represent the inherent structure of the input, which is a hierarchy of low- to high-level features. In this paper we propose to use a self-organizing competitive system, rather than an a priori determined system. Self-organization is implemented by including Földiák's anti-Hebbian learning rule in out system. Computer simulations show that this model allows for the formation of local receptive fields with orientation selectivity, and that selforganization successfully structures the competitive system.
Preview
Unable to display preview. Download preview PDF.
References
Maekawa, S., Kita, H., Nishikawa, Y.: Self-organizing extraction of hierarchical information with use of synaptic competition for the presynaptic factor. Proceedings of the World Conference on Neural Networks, Washington D. C. 2 (1995) 555–558
Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36 (1980) 192–202
Földiák, P.: Forming sparse representations by local anti-hebbian learning. Biol. Cybern. 64 (1990) 165–170
Maekawa, S., Kita, H., Nishikawa, Y.: Self-organizing learning rule with use of synaptic competition for the synaptic factor. SICE Joint Symposium (In Japanese), Okinawa (1994) 293–296
Ferster, D., Chung, S., Wheat, H.: Orientation selectivity of thalamic input to simple cells of cat visual cortex. Nature 380 (1996) 249–252
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Maekawa, S., Sawai, H. (1997). Self-organizing formation of receptive fields and competitive systems. In: Mira, J., Moreno-Díaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032511
Download citation
DOI: https://doi.org/10.1007/BFb0032511
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive