Title
Investigating Echo-State Networks Dynamics by Means of Recurrence Analysis.
Abstract
In this paper, we elaborate over the well-known interpretability issue in echo-state networks (ESNs). The idea is to investigate the dynamics of reservoir neurons with time-series analysis techniques developed in complex systems research. Notably, we analyze time series of neuron activations with recurrence plots (RPs) and recurrence quantification analysis (RQA), which permit to visualize and cha...
Year
DOI
Venue
2018
10.1109/TNNLS.2016.2630802
IEEE Transactions on Neural Networks and Learning Systems
Keywords
Field
DocType
Reservoirs,Neurons,Stability analysis,Visualization,Time series analysis,Jacobian matrices,Trajectory
Diagonal,Complex system,Time series,Jacobian matrix and determinant,Computer science,Artificial intelligence,Recurrence quantification analysis,Lyapunov exponent,Interpretability,Pattern recognition,Algorithm,Dynamical systems theory,Calculus
Journal
Volume
Issue
ISSN
29
2
2162-237X
Citations 
PageRank 
References 
8
0.44
22
Authors
3
Name
Order
Citations
PageRank
Filippo Maria Bianchi116015.76
Lorenzo Livi230425.67
Cesare Alippi31040115.84