Title :
IGLUE: an instance-based learning system over lattice theory
Author :
Njiwoua, Patrick ; Nguifo, Engelbert Mephu
Author_Institution :
Artois Univ., Lens, France
Abstract :
Concept learning is one of the most studied areas in machine learning. A lot of work in this domain deals with decision trees. In this paper, we are concerned with a different kind of technique based on Galois lattices or concept lattices. We present a new semilattice based system, IGLUE, that uses the entropy function with a tap-down approach to select concepts during the lattice construction. Then IGLUE generates new relevant numerical features by transforming initial boolean features over these concepts. IGLUE uses the new features to redescribe examples. Finally, IGLUE applies the Mahanalobe´s distance as a similarity measure between examples
Keywords :
decision theory; knowledge based systems; learning (artificial intelligence); Galois lattices; IGLUE; Mahanalobe´s distance; concept lattices; concept learning; decision trees; entropy function; initial boolean features; instance-based learning system; lattice theory; machine learning; semilattice based system; similarity measure; tap-down approach; Entropy; Lattices; Law; Learning systems; Legal factors; Lenses; Nearest neighbor searches; Neural networks; Taxonomy; Testing;
Conference_Titel :
Tools with Artificial Intelligence, 1997. Proceedings., Ninth IEEE International Conference on
Conference_Location :
Newport Beach, CA
Print_ISBN :
0-8186-8203-5
DOI :
10.1109/TAI.1997.632239
