1
$\begingroup$

I have build an autoencoder to extract from a very high dimensional (200 dimensions) space a smaller but significant representation (16 dimensions).

Now that I have these "encoded" vectors, I would like to compute some kind of similarity score, or clustering.

I am not sure which notion of distance to apply at this point. Any ideas how I can get similarity/clusters considering that I have used autoencoders?

$\endgroup$
1
$\begingroup$

You can calculate the cosine similarity between two encoded vectors you would like to compare. The cosine similarity between two vectors is defined as follows:

enter image description here

$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.