8 search results - page 1 / 2 » EM-algorithm for training of state-space models with applica... |
ESANN
2006
13 years 6 months ago
2006
In this paper, an improvement to the E step of the EM algorithm for nonlinear state-space models is presented. We also propose strategies for model structure selection when the EM-...
ICMLA
2008
13 years 6 months ago
2008
Time-series segmentation in the fully unsupervised scenario in which the number of segment-types is a priori unknown is a fundamental problem in many applications. We propose a Ba...
ICANN
2009
Springer
13 years 9 months ago
2009
Springer
Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...
DMIN
2006
13 years 6 months ago
2006
- In this paper we propose a new methodology for Cost-Benefit analysis in a multiple time series prediction problem. The proposed model is evaluated in a real world application bas...
KDD
2008
ACM
14 years 5 months ago
2008
ACM
Many time series prediction methods have focused on single step or short term prediction problems due to the inherent difficulty in controlling the propagation of errors from one ...