ILP Applications and Datasets

Contents

Each applications page contains a brief introduction to the application. This is followed by a more detailed account which describes how the examples being learnt from are represented using predicates. The page ends with links to our FTP site via which you can download the appropriate dataset. A few pages have datasets for both Golem and Progol; most, though, provide data for only one of these programs. The page also references the original papers for our experiments with the dataset, and points to LaTeX and PostScript README files which are similar in content to the page. Most of the datasets are stored as compressed TAR files.

The applications

• Learning drug structure-activity rules:
• General introduction to the drug structure-activity problem
• In drugs for Alzheimer's disease
• For drugs for inhibition of E. Coli Dihydrofolate Reductase
• In suramin analogues
• Learning rules for predicting mutagenesis
• Learning rules for predicting protein secondary structure
• Learning rules from chess databases
• Inductive Learning of Chess Rules Using Progol
• Learning rules for finite element mesh design
• Learning diagnostic rules for qualitative models of satellite power supplies
• Learning qualitative models of the U-tube system