Maximum entropy signal reconstruction with neural networks

Maximum entropy signal reconstruction with neural networks

The implementation of the maximum entropy reconstruction algorithms by means of neural networks is discussed. It is shown that the solutions of the maximum entropy problem correspond to the steady states of the appropriate Hopfield net. The choice of network parameters is discussed, and existence of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on neural networks 1992-03, Vol.3 (2), p.195-201
Hauptverfasser: Ingman, D., Merlis, Y.
Format: Artikel
Sprache:eng
Schlagworte:
Applied sciences
Biological neural networks
Computer networks
Concurrent computing
Entropy
Exact sciences and technology
Filtration
Image processing
Information, signal and communications theory
Miscellaneous
Neural networks
Parallel processing
Signal processing
Signal reconstruction
Telecommunications and information theory
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The implementation of the maximum entropy reconstruction algorithms by means of neural networks is discussed. It is shown that the solutions of the maximum entropy problem correspond to the steady states of the appropriate Hopfield net. The choice of network parameters is discussed, and existence of the maximum entropy solution is proved.< >
ISSN:1045-9227
1941-0093
DOI:10.1109/72.125860