Papers of the day   All papers

Hamiltonian Graph Networks with ODE Integrators


Oct 01 2019 DeepMind

The Hamiltonian Graph Network learns to simulate physics by incorporating ODE and Hamiltonian inductive biases into graph networks.
3 replies, 293 likes

Sep 30 2019 Kyle Cranmer

Excited to announce a new paper with Alvaro Sanchez-Gonzalez, Victor Bapst, and @PeterWBattaglia (@DeepMindAI) on "Hamiltonian Graph Networks with ODE Integrators" Gives improvements in position & energy accuracy, and zero-shot generalization.
4 replies, 238 likes

Oct 01 2019 Kyle Cranmer

Cool! @DeepMindAI is highlighting our recent paper in the context of several papers exploiting the properties of Hamiltonians. See thread, including cool new work by @DeepSpiker @irinavlh and collaborations
3 replies, 48 likes

Oct 01 2019 Carlos E. Perez

This is a big step for a new kind of science. DeepMind's new paper on Hamiltonian inspired Graph Networks will lead to greater applications of generative models in Physical domains: .
1 replies, 12 likes

Dec 02 2019 George Makrydakis

Hamiltonian Graph Networks with ODE Integrators. #ArtificialIntelligence
0 replies, 6 likes

Sep 30 2019 Sam Greydanus

Some awesome work in the same vein as our HNN paper
0 replies, 5 likes

Dec 04 2019 Kyle Cranmer

@alfcnz @samgreydanus @jasonyo 👋 @samgreydanus see you next week too. For this reading the thread, here is something related
0 replies, 3 likes

Oct 30 2019 OGAWA, Tadashi

=> "Learning Structured Models of Physics", P. Battaglia, DeepMind, Interpretable Learning in Physical Sci, IPAM, Oct 16, 2019 Video PDF Hamiltonian Graph Networks with ODE Integrators
0 replies, 1 likes

Aug 04 2019 OGAWA, Tadashi

=> "Structured intelligence (Graph ML)", Peter Battaglia, DeepMind, Hammers & Nails 2019, Weizmann, Aug 1, 2019 (25 MB/ 109 pp),P58_FILE:9309,Y Jun 2019 Graph NN: Survey/Review
1 replies, 0 likes