Modeling Trajectories with Recurrent Neural Networks

  title={Modeling Trajectories with Recurrent Neural Networks},
  author={Hao Wu and Ziyang Chen and Weiwei Sun and Baihua Zheng and Wei Wang},
Modeling trajectory data is a building block for many smart-mobility initiatives. Existing approaches apply shallow models such as Markov chain and inverse reinforcement learning to model trajectories, which cannot capture the long-term dependencies. On the other hand, deep models such as Recurrent Neural Network (RNN) have demonstrated their strength of modeling variable length sequences. However, directly adopting RNN to model trajectories is not appropriate because of the unique topological… CONTINUE READING


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 41 references


  • Deepak Ramachandran, Eyal Amir. Bayesian inverse reinforcement learning
  • pages 2586–2591,
  • 2007
Highly Influential
6 Excerpts

Neural computation

  • Sepp Hochreiter, Jürgen Schmidhuber. Long short-term memory
  • 9(8):1735–1780,
  • 1997
Highly Influential
7 Excerpts

In NIPS’13

  • Tomas Mikolov, Ilya Sutskever, +4 authors their compositionality
  • pages 3111–3119,
  • 2013
Highly Influential
4 Excerpts

Computer Science

  • Anders Gustavsson, Anders Magnuson, Björn Blomberg, Magnus Andersson, Jonas Halfvarson, Curt Tysk. On the difficulty of training recurrent neur networks
  • 52(3):337–345,
  • 2012
Highly Influential
2 Excerpts

Neural networks for machine learning

  • Geoffrey Hinton
  • Coursera video lectures,
  • 2012
Highly Influential
2 Excerpts

In AAAI’08

  • Brian D. Ziebart, Andrew L. Maas, J. Andrew Bagnell, Anind K. Dey. Maximum entropy inverse reinforcement learning
  • volume 8, pages 1433–1438,
  • 2008
Highly Influential
9 Excerpts

Similar Papers

Loading similar papers…