raminmh/liquid_time_constant_networks

Code Repository for Liquid Time-Constant Networks (LTCs)

50
/ 100
Established

This project helps researchers and machine learning practitioners benchmark and compare the performance of different continuous-time neural network models on various time-series prediction and classification tasks. You input raw time-series datasets (like sensor readings or gesture data) and it outputs model performance metrics (e.g., accuracy, loss) for different continuous-time network architectures. This is primarily for machine learning researchers or data scientists focused on advanced time-series analysis.

1,812 stars. No commits in the last 6 months.

Use this if you are a researcher or advanced practitioner experimenting with continuous-time models for sequence data and need to rigorously evaluate their performance against benchmarks.

Not ideal if you are looking for a plug-and-play solution for general time-series forecasting or classification without deep engagement with neural network architectures.

time-series-analysis neural-networks machine-learning-research predictive-modeling model-benchmarking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

1,812

Forks

327

Language

Python

License

Apache-2.0

Last pushed

Jun 03, 2024

Commits (30d)

0

Get this data via API

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

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