Analysis and Design of Echo State Networks

326 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Reservoir computing approaches to recurrent neural network training (2009, background): “An algebraic unsupervised way of generating ESN reservoirs was proposed in [119].”
Randomness in neural networks: an overview (2017, background): “Ozturk et al.(110) proposed a metric based on information–theoretic arguments by analyzing the linearized dynamic of the reservoir.”
Recent Advances in Physical Reservoir Computing: A Review (2018, methodology): “Although design principles for conventional RC, such as ESNs (Lukoševičius, 2012; Ozturk, Xu, & Príncipe, 2007) and LSMs (Maass, 2011), have been examined comprehensively, the following issues require further investigation: how to design physical reservoirs for achieving high computational…”
An overview of reservoir computing: theory, applications and implementations (2007, methodology): “In [36] is was shown that the eﬀective spectral radius of the linearized system that models the reservoir is very dependent on a constant bias input or the scaling of the input: large inputs or bias leads to a smaller eﬀective spectral radius.”
Information Processing Capacity of Dynamical Systems (2012, background): “On the other hand driving these systems on average stabilizes their dynamics 24 , and this effect increases with the input amplitude i .”