Processing unlabelled data with ANN It was my understanding that the training data has to be labeled to create a model and then label any unseen data. As in the case of using ANN, how is Google able to identify cats in Youtube videos without labeling the videos or images?
I am new to ML and tried to read some literature, but couldn't get the correct explanation. Would appreciate any pointers/explanation in more of layman terms.
 A: This paper appears relevant.
"Self-taught Learning: Transfer Learning from Unlabeled Data" by Rajat Raina, Alexis Battle, Honglak Lee, Benjamin Packer, and Andrew Y. Ng

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 self-taught 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 be learned for this representation.

