History
The heuristic approach of self-training (also known as self-learning or self-labeling) is historically the oldest approach to semi-supervised learning, with examples of applications starting in the 1960s (see for instance Scudder (1965)).
The transductive learning framework was formally introduced by Vladimir Vapnik in the 1970s. Interest in inductive learning using generative models also began in the 1970s. A probably approximately correct learning bound for semi-supervised learning of a Gaussian mixture was demonstrated by Ratsaby and Venkatesh in 1995
Semi-supervised learning has recently become more popular and practically relevant due to the variety of problems for which vast quantities of unlabeled data are available—e.g. text on websites, protein sequences, or images. For a review of recent work see a survey article by Zhu (2008).
Read more about this topic: Semi-supervised Learning
Famous quotes containing the word history:
“Only the history of free peoples is worth our attention; the history of men under a despotism is merely a collection of anecdotes.”
—Sébastien-Roch Nicolas De Chamfort (1741–1794)
“[Men say:] “Don’t you know that we are your natural protectors?” But what is a woman afraid of on a lonely road after dark? The bears and wolves are all gone; there is nothing to be afraid of now but our natural protectors.”
—Frances A. Griffin, U.S. suffragist. As quoted in History of Woman Suffrage, vol. 4, ch. 19, by Susan B. Anthony and Ida Husted Harper (1902)
“What is most interesting and valuable in it, however, is not the materials for the history of Pontiac, or Braddock, or the Northwest, which it furnishes; not the annals of the country, but the natural facts, or perennials, which are ever without date. When out of history the truth shall be extracted, it will have shed its dates like withered leaves.”
—Henry David Thoreau (1817–1862)