Evolino for recurrent support vector machines

dc.creatorSchmidhuber, Juergen
dc.creatorGagliolo, Matteo
dc.creatorWierstra, Daan
dc.creatorGomez, Faustino
dc.date2005-12-15
dc.date.accessioned2026-07-07T06:53:51Z
dc.date.available2026-07-07T06:53:51Z
dc.descriptionTraditional Support Vector Machines (SVMs) need pre-wired finite time windows to predict and classify time series. They do not have an internal state necessary to deal with sequences involving arbitrary long-term dependencies. Here we introduce a new class of recurrent, truly sequential SVM-like devices with internal adaptive states, trained by a novel method called EVOlution of systems with KErnel-based outputs (Evoke), an instance of the recent Evolino class of methods. Evoke evolves recurrent neural networks to detect and represent temporal dependencies while using quadratic programming/support vector regression to produce precise outputs. Evoke is the first SVM-based mechanism learning to classify a context-sensitive language. It also outperforms recent state-of-the-art gradient-based recurrent neural networks (RNNs) on various time series prediction tasks.
dc.description10 pages, 2 figures
dc.identifierhttps://arxiv.org/abs/cs/0512062
dc.identifierhttp://arxiv.org/abs/cs/0512062
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/105734
dc.subjectNeural and Evolutionary Computing
dc.subjectF.1.1; I.2.6
dc.titleEvolino for recurrent support vector machines
dc.typetext

Files

Collections