Recurrence Enhances the Spatial Encoding of Static Inputs in Reservoir Networks

Autor:	Jochen J. Steil, Christian Emmerich, René Felix Reinhart
Rok vydání:	2010
Předmět:	Theoretical computer science Computer science Distributed computing MathematicsofComputing_NUMERICALANALYSIS Reservoir computing Feed forward Network dynamics Nonlinear system Encoding (memory) Attractor State (computer science) Echo state network CoR-Lab Publication Extreme learning machine
Zdroj:	Artificial Neural Networks – ICANN 2010 ISBN: 9783642158216 ICANN (2)
DOI:	10.1007/978-3-642-15822-3_19
Popis:	We shed light on the key ingredients of reservoir computing and analyze the contribution of the network dynamics to the spatial encoding of inputs. Therefore, we introduce attractor-based reservoir networks for processing of static patterns and compare their performance and encoding capabilities with a related feedforward approach. We show that the network dynamics improve the nonlinear encoding of inputs in the reservoir state which can increase the task-specific performance.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d60dd7c4c6b8909077d668385d8fe1e4 https://doi.org/10.1007/978-3-642-15822-3_19 Zobrazit plný text záznamu