Corpus ID: 18507866

Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks

@inproceedings{Lee2013PseudoLabelT,
  title={Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks},
  author={D. Lee},
  year={2013}
}
  • D. Lee
  • Published 2013
  • Computer Science
We propose the simple and efficient method of semi-supervised learning for deep neural networks. Basically, the proposed network is trained in a supervised fashion with labeled and unlabeled data simultaneously. For unlabeled data, Pseudo-Labels, just picking up the class which has the maximum predicted probability, are used as if they were true labels. This is in effect equivalent to Entropy Regularization. It favors a low-density separation between classes, a commonly assumed prior for semi… Expand
Pseudo-Labeling Using Gaussian Process for Semi-Supervised Deep Learning
Semi-supervised Deep Learning Using Improved Unsupervised Discriminant Projection
Pseudo-label Selection for Deep Semi-supervised Learning
Learning by Association — A Versatile Semi-Supervised Training Method for Neural Networks
Semi-supervised Deep Learning for Fully Convolutional Networks
Deep Growing Learning
Two Semi-supervised Approaches to Malware Detection with Neural Networks
Semi-supervised Learning with Contrastive Predicative Coding
Semi-supervised Learning Using Siamese Networks
Deep Bayesian Active Semi-Supervised Learning
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 17 REFERENCES
Semi-supervised learning of compact document representations with deep networks
Extracting and composing robust features with denoising autoencoders
Deep learning via semi-supervised embedding
Classification using discriminative restricted Boltzmann machines
Representation Learning: A Review and New Perspectives
Why Does Unsupervised Pre-training Help Deep Learning?
Reducing the Dimensionality of Data with Neural Networks
The Manifold Tangent Classifier
...
1
2
...