Analysis and design of machine learning

Analysis and Design of Machine learning TechniquesManipulating or graspi ng objects seems like a trivial task for humans, asthese are motor skills of everyday lift,.. :\'evertheless, mot

Analysis and Design of Machine learning Techniques

Manipulating or graspi ng objects seems like a trivial task for humans, asthese are motor skills of everyday lift, :\'evertheless, motor skills are noteasy to learn for humans and this is also an active research topic in robot-ics However, most solutions are optimized for industrial applications and,thus, few are plausible nplanations for human learning The fundamental

challenge, that motivates Patrick Stalph, originates from the cognitive ence: How do humans learn their motor skills? The author makes a con-nection between robotics and cognitive sciences by analyzing motor ski IIlearning using implementations that could be found in the human brain - atleast to some extent Therefore three suitable machine learning algorithmsare selected - algorithms that arc plausible from a cognitive viewpoint andfeasible for the roboticist The power and scalability of those algorithms isevaluated in theon:tical simulations and more realistic scenarios with theiCub humanoid robot Convincing results confirm the applicability of theapproach, while the biological plausibility is discussed in retrospect

sci-Contents

• How do humans learn their motor skills?

• Evolutionary machine learning algorithms

• Application to simulated robots

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 Tlibingen