Semi-supervised Learning - History

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:

    “The history of American politics is littered with bodies of people who took so pure a position that they had no clout at all.”
    —Ben C. Bradlee (b. 1921)

    “Revolutions are the periods of history when individuals count most.”
    —Norman Mailer (b. 1923)

    “Books of natural history aim commonly to be hasty schedules, or inventories of God’s property, by some clerk. They do not in the least teach the divine view of nature, but the popular view, or rather the popular method of studying nature, and make haste to conduct the persevering pupil only into that dilemma where the professors always dwell.”
    —Henry David Thoreau (1817–1862)