Behavioral and Brain Sciences 21 (1):27-28 (1998)
Because “people create features to subserve the representation and categorization of objects” (abstract) Schyns et al. “provide an account of feature learning in which the components of a representation have close ties to the categorization history of the organism” (sect. 1.1). This commentary surveys self-organizing neural models that clarify this process. These models suggest how “top-down information should constrain the search for relevant dimensions/features of categorization” (sect. 3.4.2).
|Keywords||No keywords specified (fix it)|
|Categories||categorize this paper)|
References found in this work BETA
No references found.
Citations of this work BETA
No citations found.
Similar books and articles
Why Localist Connectionist Models Are Inadequate for Categorization.Robert M. French & Elizabeth Thomas - 2000 - Behavioral and Brain Sciences 23 (4):477-477.
Representations Need Self-Organizing Top-Down Expectations to Fit a Changing World.Stephen Grossberg - 1998 - Behavioral and Brain Sciences 21 (4):473-474.
Ways of Featuring in Object Categorization.Philippe G. Schyns, Robert L. Goldstone & Jean-Pierre Thibaut - 1998 - Behavioral and Brain Sciences 21 (1):41-54.
Flexible Features, Connectionism, and Computational Learning Theory.Georg Dorffner - 1998 - Behavioral and Brain Sciences 21 (1):24-25.
Do Features Arise Out of Nothing?Adriaan Tijsseling - 1998 - Behavioral and Brain Sciences 21 (1):38-39.
Flexible Categorization Requires the Creation of Relational Features.Peter F. Dominey - 1998 - Behavioral and Brain Sciences 21 (1):23-24.
Added to index2009-01-28
Total downloads10 ( #430,819 of 2,168,936 )
Recent downloads (6 months)1 ( #346,364 of 2,168,936 )
How can I increase my downloads?