fm@unl.fctunl.rccn.pt (Francisco Menezes) (06/05/89)
We have been working in machine learning algorithms that uses information theory based computations on training sets to produce decision trees. We are now interrested in the minimization of costs aproach for building decision trees, but we have been facing quite a few difficulties in finding some recent documentations on the subject. Actually, the only reference we have found is Hunt's Concept Learning System framework (Hunt, Marin and Stone, 1966). If anyone is acquainted with the subject, please send me any references or information about it. -- Francisco Jose Massa de Menezes | BITNET/Internet: fm@host.fctunl.rccn.pt CRIA - Dept. de Int. Artificial | UUCP: fm@unl.uucp UNINOVA | ARPA: fm%host.fctunl.rccn.pt@mitvma.mit.edu 2825 Monte Caparica | PSI/VMS: PSI%(+2680)05010310::FM PORTUGAL | Sound: (+351) (1) 295 4464 ext. 1360
raymond@ptolemy.arc.nasa.gov (Eric A. Raymond) (06/06/89)
I would suggest you look at Quinlin's work on ID3, a decendent of Hunt's work. Many refereces available on this exist. How about: "Learning Efficient Classification Procedures and their Application to Chess End Games", Machine Learning: An Artificial Intelligence Approach (vol. 1) (Michalski et. al., eds.) -- Eric A. Raymond (raymond@ptolemy.arc.nasa.gov) G7 C7 G7 G#7 G7 G+13 C7 GM7 Am7 Bm7 Bd7 Am7 C7 Do13 G7 C7 G7 D+13: Elmore James