Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Peter Battaglia

A Bayesian neural network predicts the dissolution of compact planetary systems


Jan 11, 2021
Miles Cranmer, Daniel Tamayo, Hanno Rein, Peter Battaglia, Samuel Hadden, Philip J. Armitage, Shirley Ho, David N. Spergel

* 8 content pages, 7 appendix and references. 8 figures. Source code at: https://github.com/MilesCranmer/bnn_chaos_model; inference code at https://github.com/dtamayo/spock 

  Access Paper or Ask Questions

Graph Networks with Spectral Message Passing


Dec 31, 2020
Kimberly Stachenfeld, Jonathan Godwin, Peter Battaglia


  Access Paper or Ask Questions

Discovering Symbolic Models from Deep Learning with Inductive Biases


Jun 19, 2020
Miles Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia, Rui Xu, Kyle Cranmer, David Spergel, Shirley Ho

* 9 pages content + 14 pages appendix/references. Supporting code found at https://github.com/MilesCranmer/symbolic_deep_learning 

  Access Paper or Ask Questions

Lagrangian Neural Networks


Mar 10, 2020
Miles Cranmer, Sam Greydanus, Stephan Hoyer, Peter Battaglia, David Spergel, Shirley Ho

* 7 pages (+2 appendix). Accepted to ICLR 2020 Deep Differential Equations Workshop. Code at github.com/MilesCranmer/lagrangian_nns 

  Access Paper or Ask Questions

Hamiltonian Graph Networks with ODE Integrators


Sep 27, 2019
Alvaro Sanchez-Gonzalez, Victor Bapst, Kyle Cranmer, Peter Battaglia


  Access Paper or Ask Questions

Learning Symbolic Physics with Graph Networks


Sep 12, 2019
Miles D. Cranmer, Rui Xu, Peter Battaglia, Shirley Ho

* 5 pages; 3 figures; submitted to Machine Learning and the Physical Sciences Workshop @ NeurIPS 2019 

  Access Paper or Ask Questions

Causal Reasoning from Meta-reinforcement Learning


Jan 23, 2019
Ishita Dasgupta, Jane Wang, Silvia Chiappa, Jovana Mitrovic, Pedro Ortega, David Raposo, Edward Hughes, Peter Battaglia, Matthew Botvinick, Zeb Kurth-Nelson


  Access Paper or Ask Questions

Compositional Imitation Learning: Explaining and executing one task at a time


Dec 04, 2018
Thomas Kipf, Yujia Li, Hanjun Dai, Vinicius Zambaldi, Edward Grefenstette, Pushmeet Kohli, Peter Battaglia

* Presented at the Learning by Instruction (LBI) Workshop at NeurIPS 2018 

  Access Paper or Ask Questions

Modeling human intuitions about liquid flow with particle-based simulation


Sep 05, 2018
Christopher J. Bates, Ilker Yildirim, Joshua B. Tenenbaum, Peter Battaglia

* Under review at PLOS Computational Biology 

  Access Paper or Ask Questions

Learning Visual Question Answering by Bootstrapping Hard Attention


Aug 01, 2018
Mateusz Malinowski, Carl Doersch, Adam Santoro, Peter Battaglia

* ECCV 2018 

  Access Paper or Ask Questions

Relational Deep Reinforcement Learning


Jun 28, 2018
Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David Reichert, Timothy Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, Peter Battaglia


  Access Paper or Ask Questions

Unsupervised Learning of 3D Structure from Images


Jun 19, 2018
Danilo Jimenez Rezende, S. M. Ali Eslami, Shakir Mohamed, Peter Battaglia, Max Jaderberg, Nicolas Heess

* Appears in Advances in Neural Information Processing Systems 29 (NIPS 2016) 

  Access Paper or Ask Questions

Graph networks as learnable physics engines for inference and control


Jun 04, 2018
Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg, Josh Merel, Martin Riedmiller, Raia Hadsell, Peter Battaglia

* ICML 2018 

  Access Paper or Ask Questions

Hyperbolic Attention Networks


May 24, 2018
Caglar Gulcehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas


  Access Paper or Ask Questions

Learning Deep Generative Models of Graphs


Mar 08, 2018
Yujia Li, Oriol Vinyals, Chris Dyer, Razvan Pascanu, Peter Battaglia

* 21 pages 

  Access Paper or Ask Questions

Imagination-Augmented Agents for Deep Reinforcement Learning


Feb 14, 2018
Théophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adria Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter Battaglia, Demis Hassabis, David Silver, Daan Wierstra


  Access Paper or Ask Questions

Learning to Perform Physics Experiments via Deep Reinforcement Learning


Aug 17, 2017
Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas


  Access Paper or Ask Questions

Learning model-based planning from scratch


Jul 19, 2017
Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sebastien Racanière, David Reichert, Théophane Weber, Daan Wierstra, Peter Battaglia


  Access Paper or Ask Questions

Visual Interaction Networks


Jun 05, 2017
Nicholas Watters, Andrea Tacchetti, Theophane Weber, Razvan Pascanu, Peter Battaglia, Daniel Zoran


  Access Paper or Ask Questions

A simple neural network module for relational reasoning


Jun 05, 2017
Adam Santoro, David Raposo, David G. T. Barrett, Mateusz Malinowski, Razvan Pascanu, Peter Battaglia, Timothy Lillicrap


  Access Paper or Ask Questions

Discovering objects and their relations from entangled scene representations


Feb 16, 2017
David Raposo, Adam Santoro, David Barrett, Razvan Pascanu, Timothy Lillicrap, Peter Battaglia

* ICLR Workshop 2017 

  Access Paper or Ask Questions