DocumentCode
1580111
Title
Neural nets for correlated and non-binary patterns: feedback from current pattern to neuron response and threshold
Author
Balter, B. ; Popova, I. ; Stalnaya, M.
Author_Institution
Space Res. Inst., Moscow, Russia
fYear
1992
Firstpage
774
Abstract
The mechanism by which the Hopfield algorithm suppresses all patterns but one is analyzed. The mechanism is modified by adapting the neuron response function and the threshold in each node to the global current pattern and to overall correlation among memory patterns. Such feedback lets the method recognize strongly correlated memories and operate on nonbinary neurons, i.e. those with more states than just (0,1)
Keywords
Hopfield neural nets; feedback; pattern recognition; recurrent neural nets; Hopfield algorithm; correlated patterns; feedback; global current pattern; neural nets; neuron response function; nonbinary neurons; strongly correlated memories; threshold; Algorithm design and analysis; Equations; Neural networks; Neurofeedback; Neurons; Pattern analysis; State feedback;
fLanguage
English
Publisher
ieee
Conference_Titel
Neuroinformatics and Neurocomputers, 1992., RNNS/IEEE Symposium on
Conference_Location
Rostov-on-Don
Print_ISBN
0-7803-0809-3
Type
conf
DOI
10.1109/RNNS.1992.268641
Filename
268641
Link To Document