Modeling the manifolds of images of handwritten digits.
IEEE T NEURAL NETWOR
65 - 74.
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.
|Title:||Modeling the manifolds of images of handwritten digits|
|Keywords:||principal components, factor analysis, autoencoder, minimum description length, density estimation, NEURAL NETWORKS, ALGORITHM|
|UCL classification:||UCL > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neuroscience Unit|
Archive Staff Only