ML Anthology

Semi-Supervised Learning

Raymond A. Board, Leonard Pitt
MLJ 1989 pp. 41-65
doi:10.1007/BF00114803 /mlj/1989/board1989mlj-semisupervised/

Abstract

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.

PDF MLJ Semantic Scholar

Cite

Text

Board and Pitt. "Semi-Supervised Learning." Machine Learning, 1989. doi:10.1007/BF00114803

Markdown

[Board and Pitt. "Semi-Supervised Learning." Machine Learning, 1989.](https://mlanthology.org/mlj/1989/board1989mlj-semisupervised/) doi:10.1007/BF00114803

BibTeX

@article{board1989mlj-semisupervised,
  title     = {{Semi-Supervised Learning}},
  author    = {Board, Raymond A. and Pitt, Leonard},
  journal   = {Machine Learning},
  year      = {1989},
  pages     = {41-65},
  doi       = {10.1007/BF00114803},
  volume    = {4},
  url       = {https://mlanthology.org/mlj/1989/board1989mlj-semisupervised/}
}