| Modelling brain emergent behaviours through coevolution of neural agents. | |
| | |
MedLine Citation:
|
PMID: 15990275 Owner: NLM Status: MEDLINE |
Abstract/OtherAbstract:
|
Recently, many research efforts focus on modelling partial brain areas with the long-term goal to support cognitive abilities of artificial organisms. Existing models usually suffer from heterogeneity, which constitutes their integration very difficult. The present work introduces a computational framework to address brain modelling tasks, emphasizing on the integrative performance of substructures. Moreover, implemented models are embedded in a robotic platform to support its behavioural capabilities. We follow an agent-based approach in the design of substructures to support the autonomy of partial brain structures. Agents are formulated to allow the emergence of a desired behaviour after a certain amount of interaction with the environment. An appropriate collaborative coevolutionary algorithm, able to emphasize both the speciality of brain areas and their cooperative performance, is employed to support design specification of agent structures. The effectiveness of the proposed approach is illustrated through the implementation of computational models for motor cortex and hippocampus, which are successfully tested on a simulated mobile robot. |
| | |
Authors:
|
Michail Maniadakis; Panos Trahanias |
Related Documents
:
|
18058035 - Should comprehensive diagnosis include idiographic understanding? 20015855 - The association between choice stepping reaction time and falls in older adults--a path... 11162295 - Effects of social-psychological factors on creative performance: the role of informatio... 12766435 - Response to shaffer (1996): the case for a 'complex systems' conceptualisation of addic... 7729385 - Estimation of variation among individuals of biological half-time of cadmium calculated... 15551365 - Reducing attenuation in exposure-response relationships by exposure modeling and groupi... |
Publication Detail:
|
Type: Comparative Study; Journal Article Date: 2005-06-29 |
Journal Detail:
|
Title: Neural networks : the official journal of the International Neural Network Society Volume: 19 ISSN: 0893-6080 ISO Abbreviation: Neural Netw Publication Date: 2006 Jun |
Date Detail:
|
Created Date: 2006-07-14 Completed Date: 2006-09-08 Revised Date: 2006-11-15 |
Medline Journal Info:
|
Nlm Unique ID: 8805018 Medline TA: Neural Netw Country: United States |
Other Details:
|
Languages: eng Pagination: 705-20 Citation Subset: IM |
Affiliation:
|
Institute of Computer Science, Foundation for Research and Technology-Hellas (FORTH), P.O. Box 1385, Heraklion, 711 10 Crete, Greece. mmaniada@ics.forth.gr |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
Animals Artificial Intelligence Behavior / physiology* Brain / cytology*, physiology Computer Simulation Hippocampus / physiology Humans Learning / physiology* Models, Neurological Motivation Motor Cortex / physiology Neural Inhibition / physiology Neural Networks (Computer)* Neural Pathways / physiology Neurons / physiology* |
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: A novel information geometric approach to variable selection in MLP networks.
Next Document: Using ICA for removal of ocular artifacts in EEG recorded from blind subjects.