Interaction Networks for Learning about Objects, Relations and Physics

Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact, supporting dynamical predictions, as well as inferences about the abstract properties of the system. Our model takes graphs as input, performs object- and relation-centric reasoning in a way that is analogous to a simulation, and is implemented using deep neural networks. We evaluate its ability to reason about several challenging physical domains: n-body problems, rigid-body collision, and non-rigid dynamics. Our results show it can be trained to accurately simulate the physical trajectories of dozens of objects over thousands of time steps, estimate abstract quantities such as energy, and generalize automatically to systems with different numbers and configurations of objects and relations. Our interaction network implementation is the first general-purpose, learnable physics engine, and a powerful general framework for reasoning about object and relations in a wide variety of complex real-world domains.

[1]  P. Johnson-Laird,et al.  Mental Models: Towards a Cognitive Science of Language, Inference, and Consciousness , 1985 .

[2]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[3]  Bernard Meltzer,et al.  Analogical Representations of Naive Physics , 1989, Artif. Intell..

[4]  Jiajun Wu,et al.  Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning , 2015, NIPS.

[5]  Barbara Solenthaler,et al.  Data-driven fluid simulations using regression forests , 2015, ACM Trans. Graph..

[6]  Jessica B. Hamrick,et al.  Simulation as an engine of physical scene understanding , 2013, Proceedings of the National Academy of Sciences.

[7]  Dan Klein,et al.  Learning to Compose Neural Networks for Question Answering , 2016, NAACL.

[8]  Nando de Freitas,et al.  Neural Programmer-Interpreters , 2015, ICLR.

[9]  Rob Fergus,et al.  Learning Physical Intuition of Block Towers by Example , 2016, ICML.

[10]  Joshua B. Tenenbaum,et al.  Building machines that learn and think like people , 2016, Behavioral and Brain Sciences.

[11]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[12]  Patrick Henry Winston,et al.  The psychology of computer vision , 1976, Pattern Recognit..

[13]  Patrick J. Hayes,et al.  The Naive Physics Manifesto , 1990, The Philosophy of Artificial Intelligence.

[14]  M. Hegarty Mechanical reasoning by mental simulation , 2004, Trends in Cognitive Sciences.

[15]  Mario Fritz,et al.  To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction , 2016, ArXiv.

[16]  D. Baraff Physically Based Modeling Rigid Body Simulation , 1992 .

[17]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[20]  Jeffrey Pennington,et al.  Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection , 2011, NIPS.

[21]  Zoubin Ghahramani,et al.  Probabilistic machine learning and artificial intelligence , 2015, Nature.

[22]  Joshua B. Tenenbaum,et al.  A Compositional Object-Based Approach to Learning Physical Dynamics , 2016, ICLR.

[23]  Charles Kemp,et al.  How to Grow a Mind: Statistics, Structure, and Abstraction , 2011, Science.

[24]  Jitendra Malik,et al.  Learning Visual Predictive Models of Physics for Playing Billiards , 2015, ICLR.

[25]  W. H. F. Barnes The Nature of Explanation , 1944, Nature.

[26]  Geoffrey E. Hinton,et al.  NeuroAnimator: fast neural network emulation and control of physics-based models , 1998, SIGGRAPH.

[27]  E. Spelke,et al.  Origins of knowledge. , 1992, Psychological review.

[28]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[29]  Ali Farhadi,et al.  Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Ali Farhadi,et al.  "What Happens If..." Learning to Predict the Effect of Forces in Images , 2016, ECCV.

[31]  Geoffrey E. Hinton,et al.  Using matrices to model symbolic relationship , 2008, NIPS.