Abstract
A model for synaptic development in natural perceptive systems based on perturbation theory has been presented during the First Italian Conference on Systemic (Camiz, 1998a; Camiz, 1998b), and some further refinements and applications have been discussed in Fourth Science European Congress (Camiz, 1999) and in International Conference on Spatial Cognition 2000 (Camiz, 2000). The underlying idea for the perturbative neural network (PNN) has been suggested by the observation that some synaptic weights of visual system can be interpreted as eigenvectors of a suitable hermitian matrix, which turns out to be the correlation matrix of input vectors.
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
Camiz, P., 1998a, A model for synaptic development based on a self organizing neural network: General treatment. In First Italian Conference on Systemics (G. Minati, ed.), Apogeo, Milano, pp. 149-159.
Camiz, P., 1998b, A model for synaptic development based on a self organizing neural network: Three applications to visual system. In First Italian Conference on Systemics (G. Minati, ed.), Apogeo, Milano, pp. 161-171.
Camiz, P., and Lo Meo, S., 1999, A perturbative neural network as a universal tool for information codification. In 4th Systems Science European Congress Systemic (L. Ferrer et al., eds.), Valencia, pp. 481-490.
Camiz, P., 2000, A neural network approach to synaptic development of labyrinth. In International Conference on Space Cognition - Cognitive Processing (M. Olivetti Belardinelli, ed.), Roma, p. 83.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer Science+Business Media New York
About this chapter
Cite this chapter
Camiz, P. (2002). Synaptic Development as a Variational Problem. In: Minati, G., Pessa, E. (eds) Emergence in Complex, Cognitive, Social, and Biological Systems. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-0753-6_7
Download citation
DOI: https://doi.org/10.1007/978-1-4615-0753-6_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5224-2
Online ISBN: 978-1-4615-0753-6
eBook Packages: Springer Book Archive