26 search results - page 4 / 6 » Simultaneous Learning of Nonlinear Manifold and Dynamical Mo... |
IDA
2003
Springer
14 years 22 days ago
2003
Springer
For a mobile robot to act autonomously, it must be able to construct a model of its interaction with the environment. Oates et al. developed an unsupervised learning method that pr...
AMFG
2005
IEEE
14 years 1 months ago
2005
IEEE
We present a new framework to represent and analyze dynamic facial motions using a decomposable generative model. In this paper, we consider facial expressions which lie on a one d...
NIPS
2004
13 years 9 months ago
2004
Multiple realizations of continuous-valued time series from a stochastic process often contain systematic variations in rate and amplitude. To leverage the information contained i...
ICANN
2009
Springer
14 years 4 days 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...
PAMI
2008
13 years 7 months ago
2008
We introduce Gaussian process dynamical models (GPDMs) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensional motio...