Title :
MGI: an incremental bottom-up algorithm
Author :
Henniche, M´hammed
Author_Institution :
LIPN, CNRS, Paris, France
fDate :
29 Nov-2 Dec 1994
Abstract :
We discuss an incremental method which learns a concept definition from examples and counter-examples. We present two bottom-up algorithms: MG and MGI that learn characteristic disjunctive definitions; MG is a non-incremental algorithm and MGI is incremental. Some experiments are performed, and a comparison with incremental top-down algorithms shows that MGI is faster, requires fewer instances to learn and found better concept definitions
Keywords :
algorithm theory; knowledge representation; learning by example; MG nonincremental bottom-up algorithm; MGI incremental bottom-up algorithm; concept definition learning; incremental top-down algorithms; learning from counter-examples; learning from examples; Algorithm design and analysis; Artificial intelligence; Bellows; Character generation; Knowledge representation; Prototypes; Space exploration; Testing;
Conference_Titel :
Intelligent Information Systems,1994. Proceedings of the 1994 Second Australian and New Zealand Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-7803-2404-8
DOI :
10.1109/ANZIIS.1994.396986
