Assumptions Used in Semi-supervised Learning
In order to make any use of unlabeled data, we must assume some structure to the underlying distribution of data. Semi-supervised learning algorithms make use of at least one of the following assumptions.
Read more about this topic: Semi-supervised Learning
Famous quotes containing the words assumptions and/or learning:
“Assumptions of male superiority are as widespread and deep rooted and every bit as crippling to the woman as the assumptions of white supremacy are to the Negro.... this is no more a man’s world than it is a white world.”
—Student Non-Violent Coordinating Committee, African American civil rights organization. SNCC Position Paper (Women in the Movement)
“Experiences in order to be educative must lead out into an expanding world of subject matter, a subject matter of facts or information and of ideas. This condition is satisfied only as the educator views teaching and learning as a continuous process of reconstruction of experience.”
—John Dewey (1859–1952)