papers AI Learner
The Github is limit! Click to go to the new site.

Richness of Deep Echo State Network Dynamics

2019-03-12
Claudio Gallicchio, Alessio Micheli

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.05174

PDF

http://arxiv.org/pdf/1903.05174


Similar Posts

Comments