Download:
|
by Xavier Giannakopoulos, Harri Valpola
http://www.cis.hut.fi/~harri/maxent00.ps.gz
Add To MetaCart
Abstract:
Abstract. A general method for state space analysis is presented where not only underlying factors generating the data are estimated, but also the dynamics behind time series in factor space are modelled. The mappings and the states are all unknown. The nonlinearity of the mappings makes the problem highly underdetermined and thus challenging. The Bayesian approach is able to find a set of mappings which has a high posterior probability. The model is very general: in principle any dynamical process can be modelled as a nonlinear state space model, and long-term dependencies can always be transformed into a model with more states and one-step dynamics. Potential applications are abundant. We present the results of experiments on real-world data.
Citations
|
800
|
Multilayer feedforward networks are universal approximators
– Hornik, Stinchcombe, et al.
- 1989
|
|
410
|
An introduction to variational methods for graphical models
– Jordan, Ghahramani, et al.
- 1997
|
|
153
|
Independent factor analysis
– Attias
- 1999
|
|
93
|
Keeping neural networks simple by minimizing the description length of the weights
– Hinton, D
- 1993
|
|
43
|
Bayesian nonlinear independent component analysis by multi-layer perceptrons
– Lappalainen, Honkela
- 2000
|
|
42
|
Developments in probabilistic modelling with neural networks – ensemble learning
– MacKay
- 1995
|
|
39
|
Learning nonlinear dynamical systems using an EM algorithm
– Ghahramani, Roweis
- 1999
|
|
37
|
Ensemble learning
– Lappalainen, Miskin
- 2000
|
|
27
|
Bayesian PCA
– Bishop
- 1999
|
|
24
|
Ensemble learning for independent component analysis
– Miskin
- 2000
|
|
14
|
Detecting strange attractors in turbulence," in Dynamical Systems and Turbulence
– Takens
- 1980
|
|
5
|
Density networks
– MacKay, Gibbs
- 1997
|
|
5
|
An EM algorithm for identification of nonlinear dynamical systems
– Roweis, Ghahramani
- 2000
|
