2013 | OriginalPaper | Chapter
Fully Complex-valued Relaxation Networks
Authors : Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
Published in: Supervised Learning with Complex-valued Neural Networks
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
The complex-valued learning algorithms described in the chapters 2 and 3 use a real-valued mean square error function as the performance measure which explicitly minimizes only the magnitude error. In addition, the mean squared error function is non-analytic in the Complex domain (not differentiable in an open set).