Abstract
Learning through adaptive value leads to environment-dependent behaviors. This paper introduces a model for stimuli centering within a visual field following the principles of this kind of learning. The neurons responsible for the eye movement execute a mapping of the visual field by means of the adaptive value of each movement. This value is the result of the interaction of biologically inspired layers, chosen in an evolutionarily and without any planning or supervision, throughout the learning process. To check the stabilization and learning abilities of the model three measurements have been used: an energy function representing weight variations; a measurement of the increment of the distances through the chosen trajectories; and, a discriminant linear analysis of the model behavior.
Preview
Unable to display preview. Download preview PDF.
References
Changeux, J.P.; Heidmann, T.; Patte, P., 1984. Learning by selection. In The Biology of Learning. Marler, P. & Terrace, H.S. (eds) Berlin. Springer-Verlag, pp. 115–133.
Reeke, G.N.; Sporns, O.; Edelman, G.E., 1990. Synthetic Neural Modeling: The “Darwin” Series of Recognition Automata. Proc. IEEE. 78(9): 1498–1530.
Hubel, D.H.; Wiesel, T.N., 1977. Functional architecture of macaque monkey visual cortex. Proc. Roy. Soc. Lon. 198:1–59.
Schwartz, E.L., 1977. Spatial mapping in the primate sensory projection: Analytic structures and relevance to perception. Biol. Cyber. 25:181–194.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Murciano, A., Zamora, J., Reviriego, M. (1993). A model for centering visual stimuli through adaptive value learning. In: Mira, J., Cabestany, J., Prieto, A. (eds) New Trends in Neural Computation. IWANN 1993. Lecture Notes in Computer Science, vol 686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56798-4_118
Download citation
DOI: https://doi.org/10.1007/3-540-56798-4_118
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56798-1
Online ISBN: 978-3-540-47741-9
eBook Packages: Springer Book Archive