1
$\begingroup$

I need to explain the word embedding layer of Keras in my paper, mathematically. I know that keras initialize the embedding vectors randomly and then update the parameters using the optimizer specified by the programmer. I want to explain my architecture in an academic paper, therefore I need to explain each layer with a formal formula. Is there a paper that explains the method in details to reference it? or can you please guide me to how to compose the method formally?

Thanks a lot

$\endgroup$
-1
$\begingroup$

I think I found the answer. The embedding layer in keras is nothing more than a set of vectors for distinct words. The keras embedding layer initializes the word embedding with some random values (the default values from a uniform distribution)and then updates the values when train the whole network. Therefore, there is no need to compose the model in details, because the backpropagation do it perfectly :)

| improve this answer | |
$\endgroup$

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.