Eigenfeatures as intermediate-level representations: The case for PCA models

Behavioral and Brain Sciences 21 (1):17-18 (1998)
  Copy   BIBTEX


Eigenfeatures are created by the principal component approach (PCA) used on objects described by a low-level code (i.e., pixels, Gabor jets). We suggest that eigenfeatures act like the flexible features described by Schyns et al. They are particularly suited for face processing and give rise to class-specific effects such as the other-race effect. The PCA approach can be modified to accommodate top-down constraints.



    Upload a copy of this work     Papers currently archived: 86,336

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

The Intermediate Level Theory of Consciousness.Jesse Prinz - 2017 - In Susan Schneider & Max Velmans (eds.), The Blackwell Companion to Consciousness. Chichester, UK: Wiley. pp. 257–271.
Intermediate representations exclude embodiment.Guy Dove - 2013 - Behavioral and Brain Sciences 36 (4):353 - 354.
Mechanical models for Lorentz group representations.N. Mukunda - 1993 - Foundations of Physics 23 (2):245-260.
On the proper treatment of connectionism.Paul Smolensky - 1988 - Behavioral and Brain Sciences 11 (1):1-23.
Hidden Markov model interpretations of neural networks.Ingmar Visser - 2000 - Behavioral and Brain Sciences 23 (4):494-495.
Full alignment of some but not all representations in dialogue.Holly P. Branigan - 2004 - Behavioral and Brain Sciences 27 (2):191-192.


Added to PP

70 (#200,207)

6 months
3 (#338,877)

Historical graph of downloads
How can I increase my downloads?

References found in this work

No references found.

Add more references