Abstract
Adaptive value (AV) is an environment-dependent variable. Therefore learning through AV shows different behaviors depending on the environment in which the model grows. In the presented model: 1) the model receives mobile visual stimuli and it should center them in the visual field, 2) the neurons responsible for the movement of eyes, execute a mapping of the visual field taking into account the AV for each movement, 3) AV is drawn from the interaction of biological like layers evolutionarily chosen, without any planning or supervision throughout the full learning process and 4) mapping changes as a function of the environment in which the model operates being able to revert when this changes.
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
Reeke, G.N.; Sporns, O.; Edelman, G.E., 1990, Synthetic Neural Modelling: The “Darwin” Series of recognition automata. Froc. IEEE. 78(9): 1498–1530.
Murciano, A.; Zamora, J.; Reviriego, M. 1993, A model for centering visual stimuli through adaptive value learning. To appear in Proceedings of IWANN93. Springer-Verlag.
Schwartz, E.L., 1977. Spatial mapping in the primate sensory projection: Analytic structures and relevance to perception. Biol. Cyber. 25: 181–194.
Hubel, D.H.; Wiesel, T.N., 1977. Functional architecture of macaque monkey visual cortex. Fro. Roy. Soc. Lon. 198: 1–59.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag London Limited
About this paper
Cite this paper
Murciano, A., Zamora, J. (1993). Learning Through Adaptive Value: A Model Working in a Variable Environment. In: Gielen, S., Kappen, B. (eds) ICANN ’93. ICANN 1993. Springer, London. https://doi.org/10.1007/978-1-4471-2063-6_10
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2063-6_10
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-19839-0
Online ISBN: 978-1-4471-2063-6
eBook Packages: Springer Book Archive