Nonlinear memory capacity of parallel time-delay reservoir computers in the processing of multidimensional signals
This work addresses reservoir computing design for multidimensional signal processing, but it appears incremental as it builds on existing robustness properties documented in the literature.
The paper tackled the reservoir design problem for delay-based reservoir computers handling multidimensional signals and parallel architectures, presenting a model linking parameters to performance and showing robustness of parallel architectures in empirical studies.
This paper addresses the reservoir design problem in the context of delay-based reservoir computers for multidimensional input signals, parallel architectures, and real-time multitasking. First, an approximating reservoir model is presented in those frameworks that provides an explicit functional link between the reservoir parameters and architecture and its performance in the execution of a specific task. Second, the inference properties of the ridge regression estimator in the multivariate context is used to assess the impact of finite sample training on the decrease of the reservoir capacity. Finally, an empirical study is conducted that shows the adequacy of the theoretical results with the empirical performances exhibited by various reservoir architectures in the execution of several nonlinear tasks with multidimensional inputs. Our results confirm the robustness properties of the parallel reservoir architecture with respect to task misspecification and parameter choice that had already been documented in the literature.