Unsupervised learning of invariant representations of faces through
Marian Stewart Bartlett and Terrence J. Sejnowski
Computational Neuroscience: International Journal of Neurobiology
Suppl. 1. J.M. Bower, ed. Academic Press, San Diego,
CA., 1996. p. 317-322.
The appearance of an object or a face changes continuously as the observer
moves through the environment or as a face changes expression or pose.
Recognizing an object or a face despite these image changes is a
challenging problem for computer vision systems, yet we perform the task
quickly and easily. This simulation investigates the ability of an
unsupervised learning mechanism to acquire representations that are
tolerant to such changes in the image. The learning mechanism finds these
representations by capturing temporal relationships between 2-D patterns.
Previous models of temporal association learning have used idealized input
representations. The input to this model consists of graylevel images of
faces. A two-layer network learned face representations that incorporated
changes of pose up to 30 degrees. A second network learned
representations that were independent of facial expression.