Title :
The application of noisy reward/penalty learning to pyramidal pRAM structures
Author :
Guan, Yelin ; Clarkson, Trevor G. ; Gorse, Denise ; Taylor, John G.
Author_Institution :
Dept. of Electron. & Electr. Eng., King´´s Coll. London, UK
Abstract :
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
Keywords :
inference mechanisms; learning (artificial intelligence); neural nets; random-access storage; noisy reward/penalty learning; pattern recognition; pyramidal pRAM structures; training; Councils; Learning; Noise figure; Noise generators; Noise level; Phase change random access memory; Pixel; Probability; Signal to noise ratio; Stochastic processes;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227099
