AI Paper Atlas

Research map / Time series / Causal and generative time series

Weak Form Generalized Hamiltonian Learning

Kevin Course, Trefor Evans, Prasanth Nair

NeurIPS 2020 · Time series › Causal and generative time series · approach: Neural differential equations · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace state regression (adjoint ODE solve) with weak form regressionFCNN pendulum model · Nonlinear pendulumtraining time: 25min 46s -> 34sImproved
replace state regression with weak form regressionFCNN pendulum model · Nonlinear pendulumstate error: 0.48 -> 0.17Improved
replace derivative regression with weak form regressionFCNN pendulum model · Nonlinear pendulum, noise 0.1state error: Diverged -> 0.17Improved
replace derivative regression with weak form regressionFCNN pendulum model · Nonlinear pendulumderivative error: 1.35 -> 0.15Improved
increase measurement frequency from 10Hz to 100Hzstate regression · Nonlinear pendulumtraining time: 4:23:59 -> 1:45:22Improved
increase measurement frequency from 10Hz to 100Hzweak form regression · Nonlinear pendulumtraining time: 0:00:32 -> 0:00:32No clear effect
increase measurement frequencyweak form regression · Nonlinear pendulumstate errorImproved
increase measurement frequencystate regression · Nonlinear pendulumstate errorHurt
use generalized Hamiltonian structure (GHNN with prior) instead of unstructured FCNNGHNN · Nonlinear pendulumderivative error: 0.43 -> 0.07Improved
use generalized Hamiltonian structure (GHNN with prior) instead of unstructured FCNNGHNN · Nonlinear pendulumstate error: 0.04 -> 0.08Hurt
use GHNN instead of HNN, which assumes energy conservationGHNN · Nonlinear pendulumstate error: 3.20 -> 0.08Improved
use GHNN instead of HNNGHNN · Duffingstate error: 1.61 -> 0.31Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy