Given a supervised problem with X, y input pairs, one can do two things for obtaining the function f that maps X with y with Neural Networks (and in general in machine learning):

  • Deploy directly a supervised learning algorithm that maps X to y

  • Deploy a (variational) auto-encoder for learning useful features, and then using these for training the supervised learning algorithm

I would like to be pointed to some papers/blogs that explain which technique is better and when or where they conduct empirical benchmarking experiments.

  • $\begingroup$ Are you asking about the advantages of using auto-encoders to pre-train models in an unsupervised way that are later trained in a supervised way to solve a classification task? You mention variational auto-encoders. Are you interested specifically in VAEs or any AE? $\endgroup$
    – nbro
    Dec 9 '20 at 10:18
  • $\begingroup$ Yes exactly, AE or VAE is the same $\endgroup$ Dec 9 '20 at 10:35

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.