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...
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...
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...
Jennifer Listgarten, Radford M. Neal, Sam T. Rowei...
Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...
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...