DANCEST 805 Lecture Notes - Lecture 12: Mixing It, 2000 United States Census, Szymon Winawer
Document Summary
Lecture: categorisation: concepts, set of objects with family resemblance, mental representation of a, concept formation: abstraction of feature set. E. g. child acquires representation of concept apple": concept learning: applying concept. Similarity-based theories: classical theories: category is represented by a series of necessary and sufficient features. Set of defining features specify category boundary: prototype- or probabilistic theories: category is represented by a series of characteristic features; Hybrid models: response to shortcomings of 3) Similarity-based vs. rule-based vs. theory-categorisation: rule-based categorization: one decides whether a test object belongs in a category by selecting out certain special features and determining whether the object satisfies a rule suggested by these features. Selecting out features of an input that are necessary for some category and then intentionally applying a rule of the general form, "if necessary feature y, then category x" (). If you apply a theory, it might be that you just apply a certain part of that theory.