Abstract
We realize a so-called developmental learning with which a motion-control system learns multiple tasks similar to each other, or advanced ones, incrementally and efficiently by tuning its behavioral mode. The system is based on a coherent neural network whose carrier frequency works as a mode-tuning parameter. The coherent neural network is a class of the complex-valued neural networks. As presented in the previous chapters, we can modulate the behavior of the coherent neural network, such as learning and processing, by changing the carrier frequency. We make the carrier frequency represent the internal mode of the system, and utilize the carrier frequency as the key to realize the developmental learning. In this chapter, we consider two tasks related to bicycle riding. The first is to ride as temporally long as the system can before it falls down (Task 1). The second is an advanced one, i.e., to ride as far as possible in a certain direction (Task 2). We compare developmental learning to learn Task 2 after Task 1 with the direct learning of Task 2. Experiments demonstrate that the developmental learning enhances the efficiency in learning in total. We confirm the effectiveness of the developmental learning utilizing the carrier frequency as the mode-tuning key in the coherent neural network.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Hirose, A. (2012). Developmental Learning with Behavioral-Mode Tuning by Carrier-Frequency Modulation. In: Complex-Valued Neural Networks. Studies in Computational Intelligence, vol 400. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27632-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-27632-3_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27631-6
Online ISBN: 978-3-642-27632-3
eBook Packages: EngineeringEngineering (R0)