Concentric ESN: Assessing the Effect of Modularity in Cycle Reservoirs
This addresses a specific bottleneck in reservoir computing for researchers, though it appears incremental as it builds on existing cycle models.
The paper tackled the problem of designing reservoir topologies for Echo State Networks by introducing a concentric modular approach, which resulted in superior predictive accuracy and memory capacity compared to single cycle and deep reservoir models.
The paper introduces concentric Echo State Network, an approach to design reservoir topologies that tries to bridge the gap between deterministically constructed simple cycle models and deep reservoir computing approaches. We show how to modularize the reservoir into simple unidirectional and concentric cycles with pairwise bidirectional jump connections between adjacent loops. We provide a preliminary experimental assessment showing how concentric reservoirs yield to superior predictive accuracy and memory capacity with respect to single cycle reservoirs and deep reservoir models.