Provides evidence that human experimentation in physical environments is effective at revealing properties of interest, and learning from observations relies on the learning goals.
Success of reasonably sized neural networks hinges on symmetry, locality, and polynomial log-probability in data from the natural world.
The Object-centric perception, prediction, and planning (OP3) framework demonstrates strong generalization to novel configurations in block stacking tasks by symmetrically processing entity representations extracted from raw visual observations.
Introduces a novel hierarchical representation of visual scenes, Physical Scene Graphs (PSGs), as well as a network for learning them from RGB movies, PSGNet, which outperforms other unsupervised methods in scene segmentation.