axelbrando/Mixture-Density-Networks-for-distribution-and-uncertainty-estimation

A generic Mixture Density Networks (MDN) implementation for distribution and uncertainty estimation by using Keras (TensorFlow)

50
/ 100
Established

This provides Jupyter notebooks that help researchers and data scientists use Mixture Density Networks to predict entire probability distributions from input data, rather than just single values. It takes various forms of data, like numerical tables or time series, and outputs a complete probability distribution along with an estimation of the prediction's uncertainty. This tool is for individuals working on advanced predictive modeling.

356 stars. No commits in the last 6 months.

Use this if you need to predict a range of possible outcomes and understand the certainty of your predictions, rather than just a single average value.

Not ideal if you are looking for a simple single-value prediction model without needing to quantify uncertainty or the full distribution.

predictive-modeling uncertainty-quantification statistical-forecasting regression-analysis data-science-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

356

Forks

92

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jun 30, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/axelbrando/Mixture-Density-Networks-for-distribution-and-uncertainty-estimation"

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