Exploiting Multiple Timescales in Hierarchical Echo State Networks

no code implementations • 11 Jan 2021 • Luca Manneschi, Matthew O. A. Ellis, Guido Gigante, Andrew C. Lin, Paolo del Giudice, Eleni Vasilaki

Echo state networks (ESNs) are a powerful form of reservoir computing that only require training of linear output weights whilst the internal reservoir is formed of fixed randomly connected neurons.

SpaRCe: Improved Learning of Reservoir Computing Systems through Sparse Representations

no code implementations • 4 Dec 2019 • Luca Manneschi, Andrew C. Lin, Eleni Vasilaki

The read-out weights and the thresholds are learned by an on-line gradient rule that minimises an error function on the outputs of the network.

BIG-bench Machine Learning Decision Making

Learning sparsity in reservoir computing through a novel bio-inspired algorithm

no code implementations • 19 Jul 2019 • Luca Manneschi, Andrew C. Lin, Eleni Vasilaki

In this work we took inspiration from the fruit fly brain to formulate a novel machine learning algorithm that is able to optimize the sparsity level of a reservoir by changing the firing thresholds of the nodes.

General Classification Memorization