A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding

@article{Zhang2016ACE,
  title={A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding},
  author={Renqiao Zhang and Jiajun Wu and Chengkai Zhang and William T. Freeman and Joshua B. Tenenbaum},
  journal={CoRR},
  year={2016},
  volume={abs/1605.01138}
}
Humans demonstrate remarkable abilities to predict physical events in complex scenes. Two classes of models for physical scene understanding have recently been proposed: “Intuitive Physics Engines”, or IPEs, which posit that people make predictions by running approximate probabilistic simulations in causal mental models similar in nature to video-game physics engines, and memory-based models, which make judgments based on analogies to stored experiences of previously encountered scenes and… CONTINUE READING
Highly Cited
This paper has 17 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 16 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 13 extracted citations

Towards intuitive rigid-body physics through parameter search

2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids) • 2017
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 25 references

Performance-optimized hierarchical models predict neural responses in higher visual cortex.

Proceedings of the National Academy of Sciences of the United States of America • 2014
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…