Learning to imitate stochastic time series in a compositional way by chaos

dc.creatorNamikawa, Jun
dc.creatorTani, Jun
dc.date2008-05-13
dc.date.accessioned2026-07-07T09:38:34Z
dc.date.available2026-07-07T09:38:34Z
dc.descriptionThis study shows that a mixture of RNN experts model can acquire the ability to generate sequences combining multiple primitive patterns by means of self-organizing chaos. By training of the model, each expert learns a primitive sequence pattern, and a gating network learns to imitate stochastic switching of the multiple primitives via a chaotic dynamics, utilizing a sensitive dependence on initial conditions. As a demonstration, we present a numerical simulation in which the model learns Markov chain switching among some Lissajous curves by a chaotic dynamics. Our analysis shows that by using a sufficient amount of training data, balanced with the network memory capacity, it is possible to satisfy the conditions for embedding the target stochastic sequences into a chaotic dynamical system. It is also shown that reconstruction of a stochastic time series by a chaotic model can be stabilized by adding a negligible amount of noise to the dynamics of the model.
dc.description24 pages, 16 figures and 2 tables
dc.identifierhttps://arxiv.org/abs/0805.1795
dc.identifierhttp://arxiv.org/abs/0805.1795
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/160856
dc.subjectChaotic Dynamics
dc.subjectAdaptation and Self-Organizing Systems
dc.titleLearning to imitate stochastic time series in a compositional way by chaos
dc.typetext

Files

Collections