I want to build a model that when given two vectors, outputs the probability of one vector being the encoded form of the other. I have 2 strategies for this: (Dataset available)

  1. I can directly feed them in concatenation to a neural network and take the output as the probability.

  2. I can train a conditional GAN with the conditional vector being the encoded vector and using the original vector as the generated one. In this case, the discriminator works as the network that I train in the first approach.

Which approach is better? Am I thinking in the right direction?

  • 1
    $\begingroup$ I haven't dealt with vector encodings, but I would suggest changing the title of your post to be more relevant. Maybe something like "What model best suits vector encoding classification" $\endgroup$
    – Recessive
    Apr 27 '21 at 4:46
  • $\begingroup$ Okayy! I'll do that $\endgroup$ Apr 27 '21 at 8:58

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.