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:
“If you look at the 150 years of modern China’s history since the Opium Wars, then you can’t avoid the conclusion that the last 15 years are the best 15 years in China’s modern history.”
—J. Stapleton Roy (b. 1935)
“One classic American landscape haunts all of American literature. It is a picture of Eden, perceived at the instant of history when corruption has just begun to set in. The serpent has shown his scaly head in the undergrowth. The apple gleams on the tree. The old drama of the Fall is ready to start all over again.”
—Jonathan Raban (b. 1942)
“Considered in its entirety, psychoanalysis won’t do. It’s an end product, moreover, like a dinosaur or a zeppelin; no better theory can ever be erected on its ruins, which will remain for ever one of the saddest and strangest of all landmarks in the history of twentieth-century thought.”
—Peter B. Medawar (1915–1987)