An efficient training method for block-diagonal recurrent neural networks is proposed. The method modifies the RPROP algorithm, originally developed for static models, in order to...
Paris A. Mastorocostas, Dimitris N. Varsamis, Cons...
Frequently, sequences of state transitions are triggered by specific signals. Learning these triggered sequences with recurrent neural networks implies storing them as different at...
Abstract. We present local conditions for input-output stability of recurrent neural networks with time-varying parameters introduced for instance by noise or on-line adaptation. T...
We present a new approach to the supervised learning of lateral interactions for the competitive layer model (CLM) dynamic feature binding architecture. The method is based on con...
We present results from experiments in using several pitch representations for jazz-oriented musical tasks performed by a recurrent neural network. We have run experiments with se...