Richness of Deep Echo State Network Dynamics
This work provides insights into optimizing deep reservoir computing for efficient recurrent neural network design, though it appears incremental in extending existing methodologies.
The study investigated how inter-reservoir connection strength enriches state dynamics in higher layers of Deep Echo State Networks, revealing its fundamental role in improving representations on benchmark datasets.
Reservoir Computing (RC) is a popular methodology for the efficient design of Recurrent Neural Networks (RNNs). Recently, the advantages of the RC approach have been extended to the context of multi-layered RNNs, with the introduction of the Deep Echo State Network (DeepESN) model. In this paper, we study the quality of state dynamics in progressively higher layers of DeepESNs, using tools from the areas of information theory and numerical analysis. Our experimental results on RC benchmark datasets reveal the fundamental role played by the strength of inter-reservoir connections to increasingly enrich the representations developed in higher layers. Our analysis also gives interesting insights into the possibility of effective exploitation of training algorithms based on stochastic gradient descent in the RC field.