TITLE

Relationship between phase and amplitude generalization errors in complex- and real-valued feedforward neural networks

AUTHOR(S)
Hirose, Akira; Yoshida, Shotaro
PUB. DATE
June 2013
SOURCE
Neural Computing & Applications;Jun2013, Vol. 22 Issue 7/8, p1357
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
We compare the generalization characteristics of complex-valued and real-valued feedforward neural networks. We assume a task of function approximation with phase shift and/or amplitude change in signals having various coherence. Experiments demonstrate that complex-valued neural networks show smaller generalization error than real-valued networks having doubled input and output neurons in particular when the signals have high coherence, that is, high degree of wave nature. We also investigate the relationship between amplitude and phase errors. It is found in real-valued networks that abrupt change in amplitude is often accompanied by steep change in phase, which is a consequence of local minima in real-valued supervised learning.
ACCESSION #
87909736

 

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics