HORUS - Horn Representations of Uncertain Systems

The project aims to develop algorithms and techniques that can be useful to learn statistical relational representations from large databases. The output of this work will a set of freely available datasets: preferred domains are in Biology and in Social Networks; a methodology for ILP-based learning in these algorithms; a set of learning modules for SRL systems; and the systematic evaluation of all these techniques in the chosen datasets plus other well-known datasets.

Funding entity: Fundação Ciência e Tecnologia (MCTES).

Reference: PTDC/EIA-EIA/100897/2008

Funding: 92812.