9 Entropy Regularization

By Yves Grandvalet Yoshua

Subfields: Optimization & Training, Information Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

1. Honglak Lee
2. Andrew Rabinovich
3. Scott E. Reed
4. Dumitru Erhan
5. Dragomir Anguelov
6. Christian Szegedy
7. Yoshua Bengio
8. Steven C. H. Hoi

In Information Theory

1. Scott E. Reed
2. Honglak Lee
3. Dumitru Erhan
4. Dragomir Anguelov
5. Christian Szegedy
6. Andrew Rabinovich

Citations in the corpus

• Training Deep Neural Networks on Noisy Labels with Bootstrapping (2014, methodology): “Minimum entropy regularization, proposed in (Grandvalet & Bengio, 2005; 2006), performs semi-supervised learning by augmenting cross-entropy loss with a term encouraging the classifier to make predictions with high confidence on the unlabeled examples 1 .”