2013 | OriginalPaper | Buchkapitel
Fully Complex-valued Multi Layer Perceptron Networks
verfasst von : Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
Erschienen in: Supervised Learning with Complex-valued Neural Networks
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This chapter focuses specifically on the study of different Complex-valued MLP (CMLP) networks and their learning algorithms in detail. Complex-valued MLPs can be broadly classified into two types depending on the way in which the complexvalued signal is handled. They are viz., Split Complex-valued MLP (SC-MLP) and Fully Complex-valued MLP (FC-MLP). In a split complex-valued MLP, the complex-valued inputs and outputs are split into two real-valued inputs using rectangular or polar coordinate systems, though the rectangular co-ordinate based splitting is the most commonly used one. On the other hand, FC-MLP neural networks process the complex-valued input signals, using fully complex-valued activation functions and weights to give fully complex-valued output signals.