Semi-supervised learning methods construct classifiers using both labeled and unlabeled training data samples. While unlabeled data samples can help to improve the accuracy of trai...
We show how to use unlabeled data and a deep belief net (DBN) to learn a good covariance kernel for a Gaussian process. We first learn a deep generative model of the unlabeled da...
In this paper we propose to study budget semi-supervised learning, i.e., semi-supervised learning with a resource budget, such as a limited memory insufficient to accommodate and/...
Zhi-Hua Zhou, Michael Ng, Qiao-Qiao She, Yuan Jian...
This paper shows that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, i.e. data are structured if knowing the ...
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...