I'm reading "Hands on machine learning" by Aurelien Geron. He stated that semi-supervised learning is:

Some photo-hosting services, such as Google Photos, are good examples of this. Once you upload all your family photos to the service, it automatically recognizes that the same person A shows up in photos 1, 5, and 11, while another person B shows up in photos 2, 5, and 7. This is the unsupervised part of the algorithm (clustering). Now all the system needs is for you to tell it who these people are. Just one label per person,4 and it is able to name everyone in every photo, which is useful for searching photos.

And the most important part:

RBMs are trained sequentially in an unsupervised manner, and then the
whole system is fine-tuned using supervised learning techniques.

So, here the semi-supervised learning process is to find clusters with an unsupervised learning algorithm then label those clusters with a supervised learning algorithm.

Question 1: if i want do this i have to impose that the number of clusters has to be the same as the number of labels that i have. In the context above, if a person A is classified as B how can I handle it in the supervised step?

I always thought that supervised learning was to use a supervised algorithm and feed it with unlabeled data to improve performances, but the book of Geron says the opposite.

Question 2: do you have some site to study the semi-supervised learning in the "Geron way"?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.