I have a bunch of users, each of them with about 100 features. My goal is to create an embedded space to compute the "distance" between users. Also, I want to be able to visualize it with Tensorboard (look this example with Word2Vec http://projector.tensorflow.org/)

However, I only find example and articles about NLP, whilst my I am not dealing with sparse matrix or "vocabulary sizes".

Since I am new to this problem, could you suggest some approaches and some papers/articles/tutorial I can start with?

  • $\begingroup$ I insist you to opt for autoencoders. They can reduce the 100 dimensional vector to 3 dimensions where you can visualize these vectors in Tensorboard. $\endgroup$ – Shubham Panchal Jun 19 '19 at 1:54
  • $\begingroup$ @ShubhamPanchal could you point me to some example/code for an autoencoder used in similar context? $\endgroup$ – Alex Jun 19 '19 at 17:37

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.