Abstract
In this Chapter, we consider all aspects of the MVN learning. We start in Section 3.1 from the specific theoretical aspects of MVN learning and from the representation of the MVN learning algorithm. Then we describe the MVN learning rules. In Section 3.2, we consider the first learning rule, which is based on the adjustment of the weights depending on the difference (in terms of the angular distance) between the arguments of the current weighted sum and the desired output. In Section 3.3, we present the error-correction learning rule for MVN. For both learning rules presented in Sections 3.2 and 3.3, we prove theorems about the convergence of the learning algorithm based on these rules. In Section 3.4, we discuss the Hebbian learning rule for MVN. Section 3.5 contains some concluding remarks.
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.
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Aizenberg, I. (2011). MVN Learning. In: Complex-Valued Neural Networks with Multi-Valued Neurons. Studies in Computational Intelligence, vol 353. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-20353-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-20353-4_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-20352-7
Online ISBN: 978-3-642-20353-4
eBook Packages: EngineeringEngineering (R0)