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)
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.
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.
Related frameworks
EmuKit/emukit
A Python-based toolbox of various methods in decision making, uncertainty quantification and...
google/uncertainty-baselines
High-quality implementations of standard and SOTA methods on a variety of tasks.
nielstron/quantulum3
Library for unit extraction - fork of quantulum for python3
IBM/UQ360
Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you...
aamini/evidential-deep-learning
Learn fast, scalable, and calibrated measures of uncertainty using neural networks!