The introduction of time-scales in Reservoir Computing, applied to isolated digits recognition

Reservoir Computing (RC) is a recent research axea, in which a untrained recurrent network of nodes is used for the recognition of temporal patterns. Contrary to Recurrent Neural Networks (RNN), where the weights of the connections between the nodes are trained, only a linear output layer is trained. We will introduce three different time-scales and show that the performance and computational complexity are highly dependent on these time-scales. This is demonstrated on an isolated spoken digits task.Reservoir Computing (RC) is a recent research axea, in which a untrained recurrent network of nodes is used for the recognition of temporal patterns. Contrary to Recurrent Neural Networks (RNN), where the weights of the connections between the nodes are trained, only a linear output layer is trained. We will introduce three different time-scales and show that the performance and computational complexity are highly dependent on these time-scales. This is demonstrated on an isolated spoken digits task.P