rakesh-yadav/PyTorch-RNN-Tutorial

PyTorch tutorial for using RNN and Encoder-Decoder RNN for time series forecasting

31
/ 100
Emerging

This package helps machine learning practitioners who are new to PyTorch understand and apply recurrent neural networks (RNNs) for time series forecasting. It takes a single stream of time-ordered data and predicts future values or sequences, allowing for hyperparameter tuning and model saving. This is for data scientists or analysts with a basic understanding of machine learning concepts but who are less familiar with PyTorch.

No commits in the last 6 months.

Use this if you need to predict future values of a single, evenly spaced time series and want to learn how to implement RNNs in PyTorch.

Not ideal if you need to forecast using multiple related time series or require a more complex, production-ready deep learning framework.

time-series-forecasting predictive-modeling financial-forecasting demand-forecasting data-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

41

Forks

3

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jan 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rakesh-yadav/PyTorch-RNN-Tutorial"

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