Analysis and Design of Machine Learning Techniques

1. Front Matter

   Pages I-XIX

   PDF

2. Introduction and Motivation

   • Patrick Stalph

   Pages 1-8

3. Background

   1. Front Matter

      Pages 9-9

      PDF

   2. Introduction to Function Approximation and Regression

      • Patrick Stalph

      Pages 11-28

   3. Elementary Features of Local Learning Algorithms

      • Patrick Stalph

      Pages 29-39

   4. Algorithmic Description of XCSF

      • Patrick Stalph

      Pages 41-53

4. Analysis and Enhancements of XCSF

   1. Front Matter

      Pages 55-55

      PDF

   2. How and Why XCSF works

      • Patrick Stalph

      Pages 57-62

   3. Evolutionary Challenges for XCSF

      • Patrick Stalph

      Pages 63-83

5. Control Applications in Robotics

   1. Front Matter

      Pages 85-85

      PDF

   2. Basics of Kinematic Robot Control

      • Patrick Stalph

      Pages 87-100

   3. Learning Directional Control of an Anthropomorphic Arm

      • Patrick Stalph

      Pages 101-123

   4. Visual Servoing for the iCub

      • Patrick Stalph

      Pages 125-135

   5. Summary and Conclusion

      • Patrick Stalph

      Pages 137-143

6. Back Matter

   Pages 145-155

   PDF

Manipulating 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.

• Human Motor Skill Learning
• Machine Learning
• Robotics

• Lehrstuhl für kognitive Modellierung, Universität Tübingen, Tübingen, Germany

  Patrick Stalph

Patrick Stalph was a Ph.D. student at the chair of Cognitive Modeling, which is led by Prof. Butz at the University of Tübingen.

Policies and ethics