SciML/DiffEqFlux.jl

Galerkin Neural ODEs

Open

#290 opened on Jun 9, 2020

View on GitHubContributor guide
 (8 comments) (0 reactions) (0 assignees)Julia (160 forks)batch import
good first issuehelp wantedlayer

Repository metrics

Stars
 (919 stars)
PR merge metrics
 (Avg merge 1d 14h) (11 merged PRs in 30d)

Description

Contributor guide

Research direction
Study the arXiv paper 2002.08071 on Galerkin Neural ODEs, understand the method, and implement it as a new layer or extension in DiffEqFlux.jl. Use existing neural ODE building blocks and add the Galerkin projection step. Validate with tests.
Tech stack
julia
Domain
machine learningai
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Unclear
Prerequisites
JuliaNeural ODE basicsGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25