A Markovian characterization of redundancy in echo state networks by PCA.
Claudio Gallicchio, Alessio Micheli · 2010
Abstract. Richness of dynamics is a desirable feature of Echo State Networks (ESNs) limited by a known high redundancy of state units activations. We show how this feature is mainly influenced by the Markovian state space organization of ESNs through a Principal Component Analysis (PCA) of the reservoir space. Relevances of principal components are coherent with Markovianity, whose role is further enlightened by investigating the strong relation among the suffix elements of the input sequence and the most relevant directions of variability in the state space. 1