Abstract
A time delayed effect in a recurrent neural network model was investigated, where the model is constructed on the binary states of each neuron and on the discrete time development. The time delay is assumed to be of integer multiple numbers in the unit of updating the time step. The model not only has a function of conventional associative memory, but also enables us to embed a new kind of multiple attractor which cannot be realised in the model without a time delayed effect.
Similar content being viewed by others
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Suemitsu, Y., Nara, S. A Note on Time Delayed Effect in a Recurrent Neural Network Model . Neur. Comp. App. 11, 137–143 (2003). https://doi.org/10.1007/s00521-003-0349-0
Issue Date:
DOI: https://doi.org/10.1007/s00521-003-0349-0