Title :
Recurrent nets for the storage of cyclic sequences
Author_Institution :
WOLF-Software, Perchtoldsdorf, Austria
Abstract :
Analytic, iterative and constructive design strategies for binary discrete-time recursive nets with synchronous update are discussed. The authors find that first-order correlation nets can be designed to exhibit a number of stable resonance modes which act as cyclic attractors. These modes represent information encoded in the network and can be used to recognize noisy sequences.<>
Keywords :
correlation theory; learning systems; neural nets; binary discrete-time recursive nets; cyclic attractors; cyclic sequences; first-order correlation nets; stable resonance modes; synchronous update; Correlation; Learning systems; Neural networks;
Conference_Titel :
Neural Networks, 1988., IEEE International Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/ICNN.1988.23828
