The application of noisy reward/penalty learning to pyramidal pRAM structures

The application of noisy reward/penalty learning to pyramidal pRAM structures

It is shown that the addition of noise during probabilistic RAM (pRAM) training develops the property of generalization and therefore the ability to recognize patterns in noisy images. Global reward/penalty learning applied to the pRAM was shown to be an efficient training method that was also hardw...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guan, Y., Clarkson, T.G., Gorse, D., Taylor, J.G.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Councils
Learning
Noise figure
Noise generators
Noise level
Phase change random access memory
Pixel
Probability
Signal to noise ratio
Stochastic processes
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:It is shown that the addition of noise during probabilistic RAM (pRAM) training develops the property of generalization and therefore the ability to recognize patterns in noisy images. Global reward/penalty learning applied to the pRAM was shown to be an efficient training method that was also hardware-reliable. Results are presented for a pRAM net which show that successful discrimination of patterns can be achieved in the presence of over 45% noise, with a 20% confidence margin.< >
DOI:10.1109/IJCNN.1992.227099