Show simple item record

dc.contributor.authorLøkse, Sigurd
dc.contributor.authorBianchi, Filippo Maria
dc.contributor.authorJenssen, Robert
dc.date.accessioned2018-07-02T08:06:50Z
dc.date.available2018-07-02T08:06:50Z
dc.date.issued2017
dc.description.abstractIn this paper, we introduce a new framework to train a class of recurrent neural network, called Echo State Network, to predict real valued time-series and to provide a visualization of the modeled system dynamics. The method consists in projecting the output of the internal layer of the network on a lower dimensional space, before training the output layer to learn the target task. Notably, we enforce a regularization constraint that leads to better generalization capabilities. We evaluate the performances of our approach on several benchmark tests, using different techniques to train the readout of the network, achieving superior predictive performance when using the proposed framework. Finally, we provide an insight on the effectiveness of the implemented mechanics through a visualization of the trajectory in the phase space and relying on the methodologies of nonlinear time-series analysis. By applying our method on well-known chaotic systems, we provide evidence that the lower dimensional embedding retains the dynamical properties of the underlying system better than the full-dimensional internal states of the network.en_US
dc.descriptionThis is a pre-print of an article published in Cognitive Computation. The final authenticated version is available online at: <a href=https://doi.org/10.1007/s12559-017-9450-z> https://doi.org/10.1007/s12559-017-9450-z</a>.en_US
dc.identifier.citationLøkse, S., Bianchi, F.M. & Jenssen, R. (2017). Training Echo State Networks with Regularization Through Dimensionality Reduction. Cognitive Computation, 1-15. https://doi.org/10.1007/s12559-017-9450-zen_US
dc.identifier.cristinIDFRIDAID 1442004
dc.identifier.doi10.1007/s12559-017-9450-z
dc.identifier.issn1866-9956
dc.identifier.issn1866-9964
dc.identifier.urihttps://hdl.handle.net/10037/13086
dc.language.isoengen_US
dc.publisherSpringer Verlag (Germany)en_US
dc.relation.ispartofLøkse, S. (2020). Leveraging Kernels for Unsupervised Learning. (Doctoral thesis). <a href=https://hdl.handle.net/10037/19911>https://hdl.handle.net/10037/19911</a>.
dc.relation.journalCognitive Computation
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/IKTPLUSS/239844/Norway/Next Generation Kernel-Based Machine Learning for Big Missing Data Applied to Earth Observation//en_US
dc.rights.accessRightsopenAccessen_US
dc.subjectVDP::Mathematics and natural science: 400::Physics: 430en_US
dc.titleTraining Echo State Networks with Regularization Through Dimensionality Reductionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record