Learning to imitate stochastic time series in a compositional way by chaos
| dc.creator | Namikawa, Jun | |
| dc.creator | Tani, Jun | |
| dc.date | 2008-05-13 | |
| dc.date.accessioned | 2026-07-07T09:38:34Z | |
| dc.date.available | 2026-07-07T09:38:34Z | |
| dc.description | This 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.description | 24 pages, 16 figures and 2 tables | |
| dc.identifier | https://arxiv.org/abs/0805.1795 | |
| dc.identifier | http://arxiv.org/abs/0805.1795 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/160856 | |
| dc.subject | Chaotic Dynamics | |
| dc.subject | Adaptation and Self-Organizing Systems | |
| dc.title | Learning to imitate stochastic time series in a compositional way by chaos | |
| dc.type | text |