Encode position inf...

Encode position information in input  


New Member
Joined: 10 months ago
Posts: 1
26/03/2020 4:38 am  

Hello all,

I have 2 vectors A and B of the same length. Vector A is the input to the classifier and vector B is an n-hot vector where the hot values represent the importance of elements in vector A. Given this scenario, is it a good idea to concat the two vectors row-wise and feed it as input to say a Dense layer?


shd I stack the vectors one below another and use a 2DConv layer with dimensions (2, vector_length) and then feed it to Dense?


should I add the two vectors elementwise and feed it to the next layer?

Any suggestions are welcomed


We use cookies to collect information about our website and how users interact with it. We’ll use this information solely to improve the site. You are agreeing to consent to our use of cookies if you click ‘OK’. All information we collect using cookies will be subject to and protected by our Privacy Policy, which you can view here.


Please Login or Register