Pregled bibliografske jedinice broj: 1515
Preprocessing by cost-sensitive literal reduction algorithm: Reduce
Preprocessing by cost-sensitive literal reduction algorithm: Reduce // Learning, Networks and Statistics / Della Riccia, G ; Lenz, H.J ; Kruse, R. (ur.).
Beč : New York (NY): Springer, 1996. str. 179-196
CROSBI ID: 1515 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Preprocessing by cost-sensitive literal reduction algorithm: Reduce
Autori
Lavrač, Nada ; Gamberger, Dragan ; Turney, Peter
Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni
Knjiga
Learning, Networks and Statistics
Urednik/ci
Della Riccia, G ; Lenz, H.J ; Kruse, R.
Izdavač
Springer
Grad
Beč : New York (NY)
Godina
1996
Raspon stranica
179-196
Ključne riječi
machine learning, literals, genetic algorithm
Sažetak
This study is concerned with whether it is possible to detect what information contained in the training data and background knowledge is relevant for solving the learning problem, and whether irrelevant information can be eliminated in preprocessing before starting the learning process. A case study of data preprocessing for a hybrid genetic algorithm shows that the elimination of irrelevant features can substantially improve the efficiency of learning. In addition, cost-sensitive feature elimination can be effective for reducing costs of induced hypotheses.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika
POVEZANOST RADA
