Learning physics from dynamical scenes

By Tomer D. Ullman, Andreas Stuhlmüller, Noah D. Goodman, Josh Tenenbaum. 2014

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Song-Chun Zhu
2. Ying Nian Wu
3. Antonio Torralba
4. Li Fei-Fei
5. Yoshua Bengio
6. Josh Tenenbaum
7. Andrea Vedaldi
8. Alan L. Yuille

Citations in the corpus

• Flexible Neural Representation for Physics Prediction (2018, background): “Recent research in computational cognitive science has posited that humans run physics simulations in their mind [5, 3, 20, 48, 21].”
• A Compositional Object-Based Approach to Learning Physical Dynamics (2016, methodology): “The top-down approach (Battaglia et al., 2013; Ullman et al., 2014; Wu et al., 2015) formulates the problem as inference over the parameters of a symbolic physics engine, while the bottom-up approach (Agrawal et al.”
• Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “cial and physical concepts can be perceived from both media as rich as videos [71] and much more sparse visual inputs [72, 73]; see examples in Figure 11.”