Incremental Learning from Positive Data
β
Steffen Lange; Thomas Zeugmann
π
Article
π
1996
π
Elsevier Science
π
English
β 835 KB
The present paper deals with a systematic study of incremental learning algorithms. The general scenario is as follows. Let c be any concept; then every infinite sequence of elements exhausting c is called positive presentation of c. An algorithmic learner successively takes as input one element of