A partially supervised learning algorithm for linearly separable systems

Author

Wan, S.J. ; Wong, S.K.M.

Author_Institution

Eastman Kodak Co., Rochester, NY, USA

Volume

14

Issue

10

fYear

1992

fDate

10/1/1992 12:00:00 AM

Firstpage

1052

Lastpage

1056

Abstract

An important aspect of human learning is the ability to select effective samples to learn and utilize the experience to infer the outcomes of new events. This type of learning is characterized as partially supervised learning. A learning algorithm of this type is suggested for linearly separable systems. The algorithm selects a subset S from a finite set X of linearly separable vectors to construct a linear classifier that can correctly classify all the vectors in X. The sample set S is chosen without any prior knowledge of how the vectors in X-S are classified. The computational complexity of the algorithm is analyzed, and the lower bound on the size of the sample set is established

Keywords

computational complexity; learning (artificial intelligence); computational complexity; linearly separable systems; lower bound; partially supervised learning; Algorithm design and analysis; Computational complexity; Computer science; Humans; Laboratories; Machine learning; Machine learning algorithms; Neural networks; Supervised learning; Vectors;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/34.159907

Filename

159907