Semi-Supervised Learning

Raymond Board, Leonard Pitt

Research output: Contribution to journalArticlepeer-review


The distribution-independent model of (supervised) concept learning due to Valiant (1984) is extended to that of semi-supervised learning (ss-learning), in which a collection of disjoint concepts is to be simultaneously learned with only partial information concerning concept membership available to the learning algorithm. It is shown that many learnable concept classes are also ss-learnable. A new technique of learning, using an intermediate oracle, is introduced. Sufficient conditions for a collection of concept classes to be ss-learnable are given.

Original languageEnglish (US)
Pages (from-to)41-65
Number of pages25
JournalMachine Learning
Issue number1
StatePublished - Oct 1989
Externally publishedYes


  • Boolean formulas
  • classification
  • concept learning
  • pac-learning
  • polynomial-time identification

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence


Dive into the research topics of 'Semi-Supervised Learning'. Together they form a unique fingerprint.

Cite this