000 03653nam a22005295i 4500
001 978-3-658-04937-9
003 DE-He213
005 20200420221257.0
007 cr nn 008mamaa
008 140206s2014 gw | s |||| 0|eng d
020 _a9783658049379
_9978-3-658-04937-9
024 7 _a10.1007/978-3-658-04937-9
_2doi
050 4 _aTJ210.2-211.495
050 4 _aTJ163.12
072 7 _aTJFM
_2bicssc
072 7 _aTJFD
_2bicssc
072 7 _aTEC004000
_2bisacsh
072 7 _aTEC037000
_2bisacsh
082 0 4 _a629.8
_223
100 1 _aStalph, Patrick.
_eauthor.
245 1 0 _aAnalysis and Design of Machine Learning Techniques
_h[electronic resource] :
_bEvolutionary Solutions for Regression, Prediction, and Control Problems /
_cby Patrick Stalph.
264 1 _aWiesbaden :
_bSpringer Fachmedien Wiesbaden :
_bImprint: Springer Vieweg,
_c2014.
300 _aXIX, 155 p. 62 illus.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
505 0 _aIntroduction and Motivation -- Introduction to Function Approximation and Regression -- Elementary Features of Local Learning Algorithms -- Algorithmic Description of XCSF -- How and Why XCSF works -- Evolutionary Challenges for XCSF -- Basics of Kinematic Robot Control -- Learning Directional Control of an Anthropomorphic Arm -- Visual Servoing for the iCub -- Summary and Conclusion.
520 _aManipulating or grasping objects seems like a trivial task for humans, as these are motor skills of everyday life. Nevertheless, motor skills are not easy to learn for humans and this is also an active research topic in robotics. However, most solutions are optimized for industrial applications and, thus, few are plausible explanations for human learning. The fundamental challenge, that motivates Patrick Stalph, originates from the cognitive science: How do humans learn their motor skills? The author makes a connection between robotics and cognitive sciences by analyzing motor skill learning using implementations that could be found in the human brain - at least to some extent. Therefore three suitable machine learning algorithms are selected - algorithms that are plausible from a cognitive viewpoint and feasible for the roboticist. The power and scalability of those algorithms is evaluated in theoretical simulations and more realistic scenarios with the iCub humanoid robot. Convincing results confirm the applicability of the approach, while the biological plausibility is discussed in retrospect.     Contents How do humans learn their motor skills Evolutionarymachinelearningalgorithms Applicationtosimulatedrobots   Target Groups Researchers interested in artificial intelligence, cognitive sciences or robotics Roboticists interested in integrating machine learning   About the Author Patrick Stalph was a Ph.D. student at the chair of Cognitive Modeling, which is led by Prof. Butz at the University of T�ubingen.
650 0 _aEngineering.
650 0 _aComputer science.
650 0 _aNeurobiology.
650 0 _aControl engineering.
650 0 _aRobotics.
650 0 _aMechatronics.
650 1 4 _aEngineering.
650 2 4 _aControl, Robotics, Mechatronics.
650 2 4 _aComputer Science, general.
650 2 4 _aNeurobiology.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9783658049362
856 4 0 _uhttp://dx.doi.org/10.1007/978-3-658-04937-9
912 _aZDB-2-ENG
942 _cEBK
999 _c53005
_d53005