Computational and Neural Models
Computational modeling (Tijsseling & Harnad 1997; Damper & Harnad 2000) has shown that many types of category-learning mechanisms (e.g. both back-propagation and competitive networks) display CP-like effects. In back-propagation nets, the hidden-unit activation patterns that "represent" an input build up within-category compression and between-category separation as they learn; other kinds of nets display similar effects. CP seems to be a means to an end: Inputs that differ among themselves are "compressed" onto similar internal representations if they must all generate the same output; and they become more separate if they must generate different outputs. The network's "bias" is what filters inputs onto their correct output category. The nets accomplish this by selectively detecting (after much trial and error, guided by error-correcting feedback) the invariant features that are shared by the members of the same category and that reliably distinguish them from members of different categories; the nets learn to ignore all other variation as irrelevant to the categorization.
Read more about this topic: Categorical Perception
Famous quotes containing the word models:
“Grandparents can be role models about areas that may not be significant to young children directly but that can teach them about patience and courage when we are ill, or handicapped by problems of aging. Our attitudes toward retirement, marriage, recreation, even our feelings about death and dying may make much more of an impression than we realize.”
—Eda Le Shan (20th century)