Title :
Extending the learnability of decision trees
Author_Institution :
Dept. of Comput. Sci., Helsinki Univ., Finland
Abstract :
The author concentrates on B. Natarajan´s (1991) framework for learning classes of total functions of discrete domains. A. Ehrenfeucht and D. Haussler (1989) have shown that a subclass of decision trees is learnable in the sense defined by L. Valiant (1984). The author generalizes their definitions to m-ary domains and shows that the learnability of restricted decision tree classifiers carries over to the extended model
Keywords :
decision theory; learning systems; trees (mathematics); decision trees; discrete domains; learnability; m-ary domains; restricted decision tree classifiers; Classification tree analysis; Computer science; Decision trees; Machine learning; Polynomials;
Conference_Titel :
Tools for Artificial Intelligence, 1991. TAI '91., Third International Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
0-8186-2300-4
DOI :
10.1109/TAI.1991.167034
