Mind Games: Game Engines as an Architecture for Intuitive Physics.

By Tomer D. Ullman, Elizabeth S. Spelke, Peter W. Battaglia, Josh Tenenbaum. 2017

247 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computational Theory and Mathematics, Developmental and Educational Psychology

How researchers see this paper

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

In Cognitive Neuroscience

In Computational Theory and Mathematics

In Developmental and Educational Psychology

Citations in the corpus

Relational inductive biases, deep learning, and graph networks (2018, methodology): “When learning, we either fit new knowledge into our existing structured representations, or adjust the structure itself to better accommodate (and make use of) the new and the old (Tenenbaum et al., 2006; Griffiths et al., 2010; Ullman et al., 2017).”
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions (2018, background): “This is supported by converging evidence from cognitive science and developmental psychology that intuitive physics and reasoning capabilities are built upon the ability to perceive objects and their interactions (Spelke, 1988; Ullman et al., 2017).”
Graph Element Networks: adaptive, structured computation and memory (2019, background): “Moreover, at test time, GENs can trade off computation time against accuracy by using smaller meshes when we do not require high precision or in easy scenarios such as when objects are far from being in collision; see Ullman et al. (2017) for a motivation from cognitive science.”
PIP: Physical Interaction Prediction via Mental Imagery with Span Selection (2021, methodology): “Many of these intuitive physics models [9, 10, 11, 12, 13, 14] are inspired by the process of mental simulation from the mental physics engine hypothesis in cognitive science research [15, 16, 17, 2].”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “[179] Tomer D Ullman, Elizabeth Spelke, Peter Battaglia, Joshua B Tenenbaum, Mind games: Game engines as an architecture for intuitive physics, Trends in Cognitive Sciences 21 (9) (2017) 649–665.”
Cognitive computational neuroscience (2018, methodology): “These models may not only be generative models in the probabilistic sense, but may be causal and compositional, supporting mental simulations of processes in the world using elements that can be recomposed to generalize to novel and hypothetical scenarios.(145,2,157) This modeling approach has been ”
Mind's Eye: Grounded Language Model Reasoning through Simulation (2022, background): “, 2018), and reasoning (Ullman et al., 2017) through interactions with the world.”