patrick-kidger/NeuralCDE

Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotlight)

44
/ 100
Emerging

This project offers a method for making predictions from complex, real-world data that changes over time, even if measurements are missing or taken at inconsistent intervals. It takes in raw, irregularly sampled time-series data and outputs predictions or classifications. Data scientists and machine learning engineers working with sensor data, financial markets, or medical records would find this useful.

700 stars. No commits in the last 6 months.

Use this if you need to build highly accurate predictive models from time-series data where observations are not uniformly spaced or have gaps.

Not ideal if your time-series data is perfectly regularly sampled and complete, as simpler methods might suffice.

time-series-analysis predictive-modeling irregular-data machine-learning-engineering data-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

700

Forks

74

Language

Python

License

Apache-2.0

Last pushed

Oct 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/patrick-kidger/NeuralCDE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.