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

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

2008-05-13

arxiv.org/abs/0805.1795v1

Nonlinear Sciences

Chaotic Dynamics

24 pages, 16 figures and 2 tables

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Learning to imitate stochastic time series in a compositional way by chaos does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning to imitate stochastic time series in a compositional way by chaos, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning to imitate stochastic time series in a compositional way by chaos will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-472085