williamgilpin/fnn

Embed strange attractors using a regularizer for autoencoders

39
/ 100
Emerging

This tool helps scientists and researchers uncover hidden variables and understand complex system dynamics from experimental time series data. You input a single or few-dimensional time series, such as temperature readings, ECG signals, or sensor data, and it outputs a higher-dimensional "embedding" that reveals the underlying behavior of the system. This is useful for anyone studying systems that generate complex, seemingly chaotic data.

135 stars. No commits in the last 6 months.

Use this if you have a time series and suspect there are more fundamental, unobserved variables driving the system's behavior that you want to reconstruct.

Not ideal if your goal is simple forecasting or anomaly detection on a time series, rather than understanding its underlying dynamical structure.

dynamical-systems chaos-theory biomedical-signals neuroscience sensor-data-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 21 / 25

How are scores calculated?

Stars

135

Forks

33

Language

Jupyter Notebook

License

Last pushed

Jun 09, 2021

Commits (30d)

0

Get this data via API

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

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