Time-shift selection for reservoir computing using a rank-revealing QR algorithm
This work addresses a specific optimization challenge in reservoir computing, offering an incremental improvement for tasks like prediction and control of nonlinear systems.
The paper tackles the problem of selecting time-shifts in reservoir computing to improve performance accuracy, presenting a technique using a rank-revealing QR algorithm that provides improved accuracy over random selection in essentially all cases.
Reservoir computing, a recurrent neural network paradigm in which only the output layer is trained, has demonstrated remarkable performance on tasks such as prediction and control of nonlinear systems. Recently, it was demonstrated that adding time-shifts to the signals generated by a reservoir can provide large improvements in performance accuracy. In this work, we present a technique to choose the time-shifts by maximizing the rank of the reservoir matrix using a rank-revealing QR algorithm. This technique, which is not task dependent, does not require a model of the system, and therefore is directly applicable to analog hardware reservoir computers. We demonstrate our time-shift selection technique on two types of reservoir computer: one based on an opto-electronic oscillator and the traditional recurrent network with a $tanh$ activation function. We find that our technique provides improved accuracy over random time-shift selection in essentially all cases.