Journal Club & Progress Club

In our Journal Club lab members take turns presenting papers they find interesting and optimally others may also find interesting and useful. The Journal Club alternates with our Progress Club where lab members present the state of their research. The target time frame for both formats is 12-15 minutes as that is often what the time slots at conferences are.

DateJ/PPresenterTitle
28.04JAline
21.04PFelix
14.04.JSebastian
07.04.PNique
31.03.JStephan
24.03.JFelix
17.03.PTim
10.03.JNique
03.03.PAline
24.02.PRobert
17.02.2021Px
10.02.2021PSebastian
03.02.2021JTim
recent and upcoming talks

JournalClub: Physics-enhanced neural networks learn order and chaos

By jannis on February 5, 2021
Choudhary, A., Lindner, J. F., Holliday, E. G., Miller, S. T., Sinha, S., & Ditto, W. L. (2020). Physics-enhanced neural networks learn order and chaos. Physical Review E, 101(6), 062207.

Artificial neural networks are universal function approximators. They can forecast dynamics, but they may need impractically many neurons to do so, especially if the dynamics is chaotic. We use neural networks that incorporate Hamiltonian dynamics to efficiently learn phase space orbits even as nonlinear systems transition from order to chaos. We demonstrate Hamiltonian neural networks on a widely used dynamics benchmark, the Hénon-Heiles potential, and on nonperturbative dynamical billiards. We introspect to elucidate the Hamiltonian neural network forecasting.

Presented on 01.07.2020 (Ioannis Iossifidis)

Links:

Restricted Content

To view this protected content, enter the password below:

No Comments »  |  Filed under: journal club, teaching  |  Tags: journalClub