Document Detail

Chained learning architectures in a simple closed-loop behavioural context.
MedLine Citation:
PMID:  17912544     Owner:  NLM     Status:  MEDLINE    
OBJECTIVE: Living creatures can learn or improve their behaviour by temporally correlating sensor cues where near-senses (e.g., touch, taste) follow after far-senses (vision, smell). Such type of learning is related to classical and/or operant conditioning. Algorithmically all these approaches are very simple and consist of single learning unit. The current study is trying to solve this problem focusing on chained learning architectures in a simple closed-loop behavioural context. METHODS: We applied temporal sequence learning (Porr B and Wörgötter F 2006) in a closed-loop behavioural system where a driving robot learns to follow a line. Here for the first time we introduced two types of chained learning architectures named linear chain and honeycomb chain. We analyzed such architectures in an open and closed-loop context and compared them to the simple learning unit. CONCLUSIONS: By implementing two types of simple chained learning architectures we have demonstrated that stable behaviour can also be obtained in such architectures. Results also suggest that chained architectures can be employed and better behavioural performance can be obtained compared to simple architectures in cases where we have sparse inputs in time and learning normally fails because of weak correlations.
Tomas Kulvicius; Bernd Porr; Florentin Wörgötter
Related Documents :
14665684 - Independent processing of the temporal and ordinal structure of movement sequences.
12814194 - The differential outcomes procedure can interfere or enhance operant rule learning.
2993944 - Neuropeptides in human memory and learning processes.
21975194 - A translational behavioral model of mood-based impulsivity: implications for substance ...
16894994 - Analysis of visual search patterns with emd metric in normalized anatomical space.
24466004 - Severity-based adaptation with limited data for asr to aid dysarthric speakers.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't     Date:  2007-10-03
Journal Detail:
Title:  Biological cybernetics     Volume:  97     ISSN:  0340-1200     ISO Abbreviation:  Biol Cybern     Publication Date:  2007 Dec 
Date Detail:
Created Date:  2008-03-13     Completed Date:  2008-05-30     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  7502533     Medline TA:  Biol Cybern     Country:  Germany    
Other Details:
Languages:  eng     Pagination:  363-78     Citation Subset:  IM    
Bernstein Centre for Computational Neuroscience, University of Göttingen, Bunsenstr. 10, 37073 Göttingen, Germany.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Artificial Intelligence*
Behavior / physiology
Computer Simulation
Learning / physiology*
Models, Biological*
Neural Networks (Computer)
Pattern Recognition, Automated*
Robotics / methods

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Antifungal efficacy of voriconazole, itraconazole and amphotericin b in experimental fusarium solani...
Next Document:  Red and green aequorins for simultaneous monitoring of Ca2+ signals from two different organelles.