Modeling the manifolds of images of handwritten digits

Geoffrey E. Hinton, Peter Dayan, Michael RevowIEEE Trans. Neural Networks 1997 · DOI · OpenReview

Abstract

This paper describes two new methods for modeling the manifolds of digitized images of handwritten digits. The models allow a priori information about the structure of the manifolds to be combined with empirical data. Accurate modeling of the manifolds allows digits to be discriminated using the relative probability densities under the alternative models. One of the methods is grounded in principal components analysis, the other in factor analysis. Both methods are based on locally linear low-dimensional approximations to the underlying data manifold. Links with other methods that model the manifold are discussed.
BibTeX
@article{hinton1997modeling,
  author = {Geoffrey E. Hinton and Peter Dayan and Michael Revow},
  title = {{Modeling the manifolds of images of handwritten digits}},
  journal = {IEEE Trans. Neural Networks},
  year = {1997},
  doi = {10.1109/72.554192},
}

Loading related content...

Figure