Rate-coded Restricted Boltzmann Machines for Face Recognition

Yee Whye Teh
Department of Computer Science
University of Toronto
Toronto M5S 2Z9, Canada

Geoffrey Hinton
Gatsby Computational Neuroscience Unit
University College London
17 Queen Square, London WC1N 3AR, UK

Abstract

We describe a neurally-inspired, unsupervised learning algorithm that builds a non-linear generative model for pairs of face images from the same individual. Individuals are then recognized by finding the highest relative probability pair among all pairs that consist of a test image and an image whose identity is known.   Our method compares favorably with other methods in the literature.  The generative model consists of a single layer of rate-coded, non-linear feature detectors and it has the property that, given a data vector, the true posterior probability distribution over the feature detector activities can be inferred rapidly without iteration or approximation.  The weights of the feature detectors are learned by comparing the correlations of pixel intensities and feature activations in tow phases:   When the network is observing real data and when it is observing reconstructions of real data generated from the feature activations.

---

Download  [pdf] [ps.gz]