What is the difference between labeled and unlabeled data?

Question

In this video from Sebastian Thrum he says that supervised learning works with \"labeled\" data and unsupervised learning works with \"unlabeled\" data. What does he mean by thi

Answer 1

There are many different problems in Machine Learning so I'll pick classification as a case in point. In classification, labelled data typically consists of a bag of multidimensional feature vectors (normally called X) and for each vector a label, Y which is often just an integer corresponding to a category eg. (face=1, non-face=-1). Unlabelled data misses the Y component. There are many scenarios where unlabelled data is plentiful and easily obtained but labelled data often requires a human/expert to annotate.