Learning Nonlinear Dynamic Models

John Langford, Ruslan Salakhutdinov, Tong Zhang

ICML 2009 pp. 593-600

doi:10.1145/1553374.1553451 /icml/2009/langford2009icml-learning/

Abstract

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 high-dimensional video data, yielding results superior to standard alternatives.

PDF ICML Semantic Scholar

Cite

Text

Langford et al. "Learning Nonlinear Dynamic Models." International Conference on Machine Learning, 2009. doi:10.1145/1553374.1553451

Markdown

[Langford et al. "Learning Nonlinear Dynamic Models." International Conference on Machine Learning, 2009.](https://mlanthology.org/icml/2009/langford2009icml-learning/) doi:10.1145/1553374.1553451

BibTeX

@inproceedings{langford2009icml-learning,
  title     = {{Learning Nonlinear Dynamic Models}},
  author    = {Langford, John and Salakhutdinov, Ruslan and Zhang, Tong},
  booktitle = {International Conference on Machine Learning},
  year      = {2009},
  pages     = {593-600},
  doi       = {10.1145/1553374.1553451},
  url       = {https://mlanthology.org/icml/2009/langford2009icml-learning/}
}