Deep Learning via Semi-Supervised Embedding
Abstract
We show how nonlinear embedding algorithms popular for use with shallow semi-supervised learning techniques such as kernel methods can be applied to deep multi-layer architectures, either as a regularizer at the output layer, or on each layer of the architecture. This provides a simple alternative to existing approaches to deep learning whilst yielding competitive error rates compared to those methods, and existing shallow semi-supervised techniques.
Cite
Text
Weston et al. "Deep Learning via Semi-Supervised Embedding." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390303Markdown
[Weston et al. "Deep Learning via Semi-Supervised Embedding." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/weston2008icml-deep/) doi:10.1145/1390156.1390303BibTeX
@inproceedings{weston2008icml-deep,
title = {{Deep Learning via Semi-Supervised Embedding}},
author = {Weston, Jason and Ratle, Frédéric and Collobert, Ronan},
booktitle = {International Conference on Machine Learning},
year = {2008},
pages = {1168-1175},
doi = {10.1145/1390156.1390303},
url = {https://mlanthology.org/icml/2008/weston2008icml-deep/}
}