TY - GEN
T1 - Learning nonlinear dynamic models
AU - Langford, John
AU - Salakhutdinov, Ruslan
AU - Zhang, Tong
PY - 2009
Y1 - 2009
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=70049102579&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70049102579&partnerID=8YFLogxK
U2 - 10.1145/1553374.1553451
DO - 10.1145/1553374.1553451
M3 - Conference contribution
AN - SCOPUS:70049102579
SN - 9781605585161
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the 26th Annual International Conference on Machine Learning, ICML'09
PB - Association for Computing Machinery
T2 - 26th Annual International Conference on Machine Learning, ICML'09
Y2 - 14 June 2009 through 18 June 2009
ER -