Over ons

Consortium

Team

Vlaams Beleidsplan AI

Maak kennis met onze Alumni

Contact

<h5>Description:</h5>
<p>DeepMTP is a python package for multi-target prediction (MTP) problems. In contrast to all other published software that is compatible with at most two MTP problem settings, DeepMTP is designed to be compatible with the majority of them (Currently 6 MTP settings have been tested). This is achieved by utilizing a flexible two-branch neural network architecture, capable of adapting to the different needs of MTP settings. The implementation is combined with additional functionality that helps users train models with minimal effort (built-it hyperparameter optimization, experiment logging, etc.). An extension of the package was also implemented using the streamlit framework, enabling users to use the DeepMTP package without any programming experience.</p>

<h5>More Information:</h5>
<ul>
<li><strong>Grand Challenge/Workpackage(s)</strong>: <a href="/nl/onderzoek/onderzoeksuitdagingen-2019-2023/ai-driven-data-science"[entry:58:/onderzoek/onderzoeksutidagingen-2019-2023/ai-driven-data-science]data-entry-id="58">GC1</a> - WP4</li>
<li><strong>Responsible Research Lead</strong>: <a href="mailto:Willem.Waegeman@UGent.be" target="_blank" rel="noopener">Willem Waegeman</a>, <a href="mailto:Bernard.DeBaets@UGent.be" target="_blank" rel="noopener">Bernard De Baets</a></li>
<li><strong>Authors</strong>: <a href="mailto:Dimitrios.Iliadis@UGent.be" target="_blank" rel="noopener">Dimitrios Iliadis</a></li>
<li><strong>Programming Language</strong>: Python</li>
<li><a href="https://github.com/diliadis/DeepMTP" target="_blank" rel="noopener">Link to the repository 1</a></li>
<li><a href="https://github.com/diliadis/DeepMTP_gui" target="_blank" rel="noopener">Link to the repository 2 (GUI)</a></li>
<li><strong>Categories</strong>: Supervised learning, Recommender systems</li>
</ul>