The Manifold Tangent Classifier
Abstract
We combine three important ideas present in previous work for building classi- fiers: the semi-supervised hypothesis (the input distribution contains information about the classifier), the unsupervised manifold hypothesis (data density concen- trates near low-dimensional manifolds), and the manifold hypothesis for classifi- cation (different classes correspond to disjoint manifolds separated by low den- sity). We exploit a novel algorithm for capturing manifold structure (high-order contractive auto-encoders) and we show how it builds a topological atlas of charts, each chart being characterized by the principal singular vectors of the Jacobian of a representation mapping. This representation learning algorithm can be stacked to yield a deep architecture, and we combine it with a domain knowledge-free version of the TangentProp algorithm to encourage the classifier to be insensitive to local directions changes along the manifold. Record-breaking classification results are obtained.
Cite
Text
Rifai et al. "The Manifold Tangent Classifier." Neural Information Processing Systems, 2011.Markdown
[Rifai et al. "The Manifold Tangent Classifier." Neural Information Processing Systems, 2011.](https://mlanthology.org/neurips/2011/rifai2011neurips-manifold/)BibTeX
@inproceedings{rifai2011neurips-manifold,
title = {{The Manifold Tangent Classifier}},
author = {Rifai, Salah and Dauphin, Yann N. and Vincent, Pascal and Bengio, Yoshua and Muller, Xavier},
booktitle = {Neural Information Processing Systems},
year = {2011},
pages = {2294-2302},
url = {https://mlanthology.org/neurips/2011/rifai2011neurips-manifold/}
}