Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published November 15, 2002 | Published
Journal Article Open

EMPATH: A Neural Network that Categorizes Facial Expressions

Abstract

There are two competing theories of facial expression recognition. Some researchers have suggested that it is an example of "categorical perception." In this view, expression categories are considered to be discrete entities with sharp boundaries, and discrimination of nearby pairs of expressive faces is enhanced near those boundaries. Other researchers, however, suggest that facial expression perception is more graded and that facial expressions are best thought of as points in a continuous, low-dimensional space, where, for instance, "surprise" expressions lie between "happiness" and "fear" expressions due to their perceptual similarity. In this article, we show that a simple yet biologically plausible neural network model, trained to classify facial expressions into six basic emotions, predicts data used to support both of these theories. Without any parameter tuning, the model matches a variety of psychological data on categorization, similarity, reaction times, discrimination, and recognition difficulty, both qualitatively and quantitatively. We thus explain many of the seemingly complex psychological phenomena related to facial expression perception as natural consequences of the tasks' implementations in the brain.

Additional Information

© 2002 The MIT Press. We thank Stevan Harnad, Bill Kristan, Paul Munro, Alice O'Toole, Terry Sejnowski, and Gary's Unbelievable Research Unit (GURU) for helpful comments on previous versions of this manuscript. We also thank Andrew Young for permission to use the human data plotted in Figures 2, 3, 7a, and 8. We are also grateful to Paul Ekman for providing us with the Pictures of Facial Affect. This research was funded by NIMH grant MH57075 to GWC.

Attached Files

Published - DAIjcn02.pdf

Files

DAIjcn02.pdf
Files (452.5 kB)
Name Size Download all
md5:67d110420504897877dfa42697c26af5
452.5 kB Preview Download

Additional details

Created:
August 21, 2023
Modified:
October 16, 2023