Sciweavers

NN
2010
Springer

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

13 years 2 months ago
Learning to imitate stochastic time series in a compositional way by chaos
This study shows that a mixture of RNN experts model can acquire the ability to generate sequences that are combination of 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.
Jun Namikawa, Jun Tani
Added 29 Jan 2011
Updated 29 Jan 2011
Type Journal
Year 2010
Where NN
Authors Jun Namikawa, Jun Tani
Comments (0)