Adaptive Neurodynamics

H...............H

Show simple item record

dc.contributor.author Negrello, Mario
dc.contributor.author Pasemann, Frank
dc.contributor.author Hülse, Martin
dc.contributor.editor Yang, A.
dc.date.accessioned 2008-02-28T16:49:27Z
dc.date.available 2008-02-28T16:49:27Z
dc.date.issued 2008-01
dc.identifier.citation Negrello , M , Pasemann , F & Hülse , M 2008 , ' Adaptive Neurodynamics ' . in A Yang (ed.) , S. Shan . IGI Global Publishing , pp. 82-108 . en
dc.identifier.other PURE: 75731
dc.identifier.other dspace: 2160/516
dc.identifier.uri http://hdl.handle.net/2160/516
dc.identifier.uri http://www.cybertech-pub.com/books/details.asp?id=7316 en
dc.description Negrello, M., Huelse, M., Pasemann, F.: Adaptive Neurodynamics. In: S. Shan, A. Yang (Eds.) Applications of Complex Adaptive Systems, IGI Global Publishing, USA, 82-108, 2008. en
dc.description.abstract Neurodynamics is the application of dynamical systems theory (DST) to the analysis of the structure and function of recurrent neural networks (RNNs). In this chapter, we present RNNs artificially evolved for the control of autonomous robots (evolutionary robotics [ER]) and further analyzed within dynamical systems tenets (neurodynamics). We search for the characteristic dynamical entities (e.g., attractor landscapes) that arise from being-environment interactions that underpin the adaptation of animat's (biologically inspired robots). In that way, when an efficient controller is evolved, we are able to pinpoint the reasons for its success in terms of the dynamical characteristics of the evolved networks. The approach is exemplified with the dynamical analysis of an evolved network controller for a small robot that maximizes exploration, while controlling its energy reserves, by resorting to different periodic attractors. Contrasted to other approaches to the study of neural function, neurodynamics' edge results from causally traceable explanations of behavior, contraposed to just orrelations. We conclude with a short discussion about other approaches for artificial brain design, challenges, and future perspectives for neurodynamics. en
dc.format.extent 27 en
dc.language.iso eng
dc.publisher IGI Global Publishing
dc.relation.ispartof S. Shan en
dc.title Adaptive Neurodynamics en
dc.type Text en
dc.type.publicationtype Book chapter en
dc.contributor.institution Department of Computer Science en
dc.contributor.institution Intelligent Robotics Group en


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Cadair


Advanced Search

Browse

My Account