Chasing the Echo State Property

11/27/2018
by   Claudio Gallicchio, et al.
0

Reservoir Computing (RC) provides an efficient way for designing dynamical recurrent neural models. While training is restricted to a simple output component, the recurrent connections are left untrained after initialization, subject to stability constraints specified by the Echo State Property (ESP). Literature conditions for the ESP typically fail to properly account for the effects of driving input signals, often limiting the potentialities of the RC approach. In this paper, we study the fundamental aspect of asymptotic stability of RC models in presence of driving input, introducing an empirical ESP index that enables to easily analyze the stability regimes of reservoirs. Results on two benchmark datasets reveal interesting insights on the dynamical properties of input-driven reservoirs, suggesting that the actual domain of ESP validity is much wider than what covered by literature conditions commonly used in RC practice.

READ FULL TEXT
research
06/04/2020

Sparsity in Reservoir Computing Neural Networks

Reservoir Computing (RC) is a well-known strategy for designing Recurren...
research
01/03/2020

Memory-Loss is Fundamental for Stability and Distinguishes the Echo State Property Threshold in Reservoir Computing Beyond

Reservoir computing, a highly successful neuromorphic computing scheme u...
research
06/23/2020

Lipschitz Recurrent Neural Networks

Differential equations are a natural choice for modeling recurrent neura...
research
03/12/2019

Richness of Deep Echo State Network Dynamics

Reservoir Computing (RC) is a popular methodology for the efficient desi...
research
03/20/2017

Empirical Analysis of the Necessary and Sufficient Conditions of the Echo State Property

The Echo State Network (ESN) is a specific recurrent network, which has ...
research
09/09/2023

Transitions in echo index and dependence on input repetitions

The echo index counts the number of simultaneously stable asymptotic res...
research
04/28/2023

Input-to-State Stability in Probability

Input-to-State Stability (ISS) is fundamental in mathematically quantify...

Please sign up or login with your details

Forgot password? Click here to reset