Abstract
Nearly all phenomena of the natural world involve systems whose behavior varies through time. In some cases the rules governing the behavior are themselves opaque, but in many cases complexity can arise from relatively simple rules. The most primitive biological information processing systems evolved to meet the necessities of survival. From sense data to action, flight or the capture of prey, there is a gap that was bridged by the evolution of adaptive control systems based on circuits of simple neural components. A vital computational characteristic of such neural circuitry is the ability to model non-linear dynamic systems.
Let the biologists go as far as they can and let us go as far as we can. Some day the two will meet.
Sigmund Freud
(Origins of Psychoanalysis)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer-Verlag London
About this chapter
Cite this chapter
Dracopoulos, D.C. (1997). Neuromodels of Dynamic Systems. In: Evolutionary Learning Algorithms for Neural Adaptive Control. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0903-7_5
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0903-7_5
Publisher Name: Springer, London
Print ISBN: 978-3-540-76161-7
Online ISBN: 978-1-4471-0903-7
eBook Packages: Springer Book Archive