Sciweavers

Share
ICML
2007
IEEE

Self-taught learning: transfer learning from unlabeled data

9 years 12 months ago
Self-taught learning: transfer learning from unlabeled data
We present a new machine learning framework called "self-taught learning" for using unlabeled data in supervised classification tasks. We do not assume that the unlabeled data follows the same class labels or generative distribution as the labeled data. Thus, we would like to use a large number of unlabeled images (or audio samples, or text documents) randomly downloaded from the Internet to improve performance on a given image (or audio, or text) classification task. Such unlabeled data is significantly easier to obtain than in typical semi-supervised or transfer learning settings, making selftaught learning widely applicable to many practical learning problems. We describe an approach to self-taught learning that uses sparse coding to construct higher-level features using the unlabeled data. These features form a succinct input representation and significantly improve classification performance. When using an SVM for classification, we further show how a Fisher kernel can ...
Rajat Raina, Alexis Battle, Honglak Lee, Benjamin
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2007
Where ICML
Authors Rajat Raina, Alexis Battle, Honglak Lee, Benjamin Packer, Andrew Y. Ng
Comments (0)
books