jambo6/neuralRDEs

Code for: "Neural Rough Differential Equations for Long Time Series", (ICML 2021)

32
/ 100
Emerging

This project helps machine learning researchers and practitioners working with very long time series data. It takes raw, lengthy time series and processes them using a technique called Neural Rough Differential Equations, outputting predictions or classifications faster than traditional methods. The end user is typically a data scientist or ML engineer focused on time series analysis in fields like healthcare or finance.

123 stars. No commits in the last 6 months.

Use this if you need to train machine learning models on extremely long time series datasets and find that current methods are too slow.

Not ideal if you are working with short time series or if you prefer a simpler, out-of-the-box solution without hyperparameter tuning.

time-series-analysis predictive-modeling healthcare-analytics financial-forecasting scientific-modeling
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

123

Forks

15

Language

Jupyter Notebook

License

Last pushed

May 11, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jambo6/neuralRDEs"

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