USE Tutorials

Machine learning models can largely outperform classical algorithms to make predictions about complexe problems, e.g. recognizing trees (which can vary a lot depending on the season, the species…). To do so, they learn from data (either from examples or experience) instead of following a well-defined sequence of instructions (like a cooking recipe). We humans do the same to teach our kids to recognize trees: we do not provide instructions but examples.

Explore the features


Get Started

Learn the basics of the package here.


Binary classification

Explain a binary classifier with the Adult dataset


Multi-class classification

Explain a multi-class classifier with the Iris dataset.



Explain a regressor with the Boston dataset.



Explain an image classifier with the MNIST dataset.



Explain correlations in a multidimensional context.


Conduct real-world analyses


Heart disease

Explain the forecast for heart disease diagnosis.



Explain a classifier that predicts the presence of diabete.


Compare to alternatives


Partial Dependence Plot

Comparison with Partial Dependency Plot to understand marginal effect of variables.


Code source on GitHub

You can find onGitHub : theIntroduction, Installation guide, User guide (Measuring model influence, Evaluating model reliability, Support for image classification), Authors and License.


This work is done at the Toulouse Mathematics Institute. It is supported by the Centre National de la Recherche Scientifique (CNRS) and in collaboration with the Artificial and Natural  Intelligence Toulouse



Contact us

Mathematics Institute

118 Rte de Narbonne
31400 Toulouse - FRANCE


Pin It on Pinterest

Share This