An extension to the Hayashi coupled oscillator network training rule
Edward M. Corwin, A.M. Logar, William J. B. Oldham · 2002
A variety of recurrent network architectures have been developed and applied to the problem of time series prediction. One particularly interesting network was developed by Hayashi (1994). Hayashi presented a network of coupled oscillators and a training rule for the network. His derivation was based on continuous mathematics and provided a mechanism for updating the weights into the output nodes. The work presented here gives an alternative derivation of Hayashi's learning rule based on discrete mathematics as well an extension to the learning rule which allows for updating of all weights in the network.