MODELING THE MANIFOLDS OF IMAGES OF HANDWRITTEN DIGITS

Citation
Ge. Hinton et al., MODELING THE MANIFOLDS OF IMAGES OF HANDWRITTEN DIGITS, IEEE transactions on neural networks, 8(1), 1997, pp. 65-74
Citations number
28
Categorie Soggetti
Computer Application, Chemistry & Engineering","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Hardware & Architecture","Computer Science Theory & Methods
ISSN journal
10459227
Volume
8
Issue
1
Year of publication
1997
Pages
65 - 74
Database
ISI
SICI code
1045-9227(1997)8:1<65:MTMOIO>2.0.ZU;2-5
Abstract
This paper describes two new methods for modeling the manifolds of dig itized images of handwritten digits. The models allow a priori informa tion about the structure of the manifolds to be combined with empirica l data. Accurate modeling of the manifolds allows digits to be discrim inated using the relative probability densities under the alternative models. One of the methods is grounded in principal components analysi s, the other in factor analysis. Both methods are based on locally lin ear low-dimensional approximations to the underlying data manifold. Li nks with other methods that model the manifold are discussed.