LIME
Lime is an ILP system that induces first order logic programs
from a set of ground examples. It incorporates techniques such
as : using the Q heuristic to handle noise and fixed example sizes, and
preprocessing the input examples to learn information to
restrict the search space. In so doing lime demonstrates the
efficacy of such techniques.
Related Publications
- Eric McCreath and Arun Sharma,"Lime: A System for Learning Relations" to appear in
The 9th International Workshop on Algorithmic Learning Theory,
Otzenhausen, Germany,
October 8 - 10, 1998,
Proceedings will be published as a volume in the Lecture Notes in
Artificial Intelligence, Springer-Verlag
ALT98 (ps format)
- Eric McCreath and Arun Sharma,"ILP with Noise and fixed Example Size : a Bayesian Approach" appeard in IJCAI97 (ps format)
System Demo
A cgi demo(currently not working)
is set up so you may have a quick look at Lime
with out down loading the entire code. Note, the search parameters
are set to small values so Lime doesn't take up to much processor
time on the schools servers.
Down Load
Lime 1.0 is available to
down load
free of charge for personal use, educational use, or machine learning research .
If you wish to use it for commercial gain then you must contact Eric McCreath.
Lime is provided "as is" without express or implied warranty.
Please email a short note to say you downloaded the system. If you
wish to be added to a LIME mailing list just let me know. The
list will inform people of updates to the system.
I am also interested in any feedback and bug reports for LIME.