You are here: Home / About / About

We built this web site as a repository for your machine learning data. Upload your data, find interesting data sets, define learning tasks and challenges, exchange solutions and compare yourself against other methods.

This repository manages the following types of objects.

• Data Sets Raw data as a collection of similarily structured objects.
• Material and Methods Descriptions of the computational pipeline.
• Learning Tasks Learning tasks defined on raw data.
• Challenges Collections of tasks which have a particular theme.

What to do next:

• Learn more about why we built this website.
• Browse the repository.
• Upload a data set.
• Describe your new method.
• Learn more about our HDF5 data format.

For the more advanced user:

• Define a learning task for a particular dataset.
• We use python style indices to represent features and splits
• See which evaluation measures we support.
• Define your own Challenge.

• Motivation
• Related Projects
• Data Licenses Explained
• Our HDF5 format
• Impressum
• TOS

This project is supported by PASCAL (Pattern Analysis, Statistical Modelling and Computational Learning)

http://www.pascal-network.org/.