caa a22 4500 463244974 CHVBK 20180405153323.0 cr unu---uuuuu 170326e20071201xx s 000 0 eng 10.1007/s00422-007-0176-y doi (NATIONALLICENCE)springer-10.1007/s00422-007-0176-y Chained learning architectures in a simple closed-loop behavioural context [Elektronische Daten] [Tomas Kulvicius, Bernd Porr, Florentin Wörgötter] 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. Springer-Verlag, 2007 Temporal sequence learning nationallicence Sparse inputs nationallicence Weak correlations nationallicence Line-following nationallicence Driving robot nationallicence Kulvicius Tomas Bernstein Centre for Computational Neuroscience, University of Göttingen, Bunsenstr. 10, 37073, Göttingen, Germany aut Porr Bernd Department of Electronics and Electrical Engineering, University of Glasgow, GT12 8LT, Glasgow, Scotland, UK aut Wörgötter Florentin Bernstein Centre for Computational Neuroscience, University of Göttingen, Bunsenstr. 10, 37073, Göttingen, Germany aut Biological Cybernetics Springer-Verlag 97/5-6(2007-12-01), 363-378 0340-1200 97:5-6<363 2007 97 422 https://doi.org/10.1007/s00422-007-0176-y text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s00422-007-0176-y text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Kulvicius Tomas Bernstein Centre for Computational Neuroscience, University of Göttingen, Bunsenstr. 10, 37073, Göttingen, Germany aut NATIONALLICENCE 700 1- Porr Bernd Department of Electronics and Electrical Engineering, University of Glasgow, GT12 8LT, Glasgow, Scotland, UK aut NATIONALLICENCE 700 1- Wörgötter Florentin Bernstein Centre for Computational Neuroscience, University of Göttingen, Bunsenstr. 10, 37073, Göttingen, Germany aut NATIONALLICENCE 773 0- Biological Cybernetics Springer-Verlag 97/5-6(2007-12-01), 363-378 0340-1200 97:5-6<363 2007 97 422 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer