Reservoir Computers Modal Decomposition and Optimization
This work addresses optimization challenges in reservoir computing, a domain-specific area, by introducing a novel parametric approach for mode manipulation.
The authors tackled the problem of optimizing reservoir computers by decomposing the reservoir dynamics into independent modes based on network eigenvalues, which can be designed and optimized along with time shifts. They demonstrated that manipulating these modes leads to dramatic reductions in training error.
The topology of a network associated with a reservoir computer is often taken so that the connectivity and the weights are chosen randomly. Optimization is hardly considered as the parameter space is typically too large. Here we investigate this problem for a class of reservoir computers for which we obtain a decomposition of the reservoir dynamics into modes, which can be computed independently of one another. Each mode depends on an eigenvalue of the network adjacency matrix. We then take a parametric approach in which the eigenvalues are parameters that can be appropriately designed and optimized. In addition, we introduce the application of a time shift to each individual mode. We show that manipulations of the individual modes, either in terms of the eigenvalues or the time shifts, can lead to dramatic reductions in the training error.