Learning nonlinear dynamic models

We present a novel approach for learning nonlinear dynamic models, which leads to a new set of tools capable of solving problems that are otherwise difficult. We provide theory showing this new approach is consistent for models with long range structure, and apply the approach to motion capture and highdimensional video data, yielding results superior to standard alternatives.

• Type: Conference
• Year: 2009
• Where: ICML
• Authors: John Langford, Ruslan Salakhutdinov, Tong Zhang
• Keywords: ICML 2009, Long Range Structure, Machine Learning, Nonlinear Dynamic Models