Is there a difference between keras masking () and embedding (mask_zero = true) layers?

Question

The documentation for the Embedding layer is here:

https://keras.io/layers/embeddings/

and the documentation for the Masking layer is here:

https://keras.io/layers/recurrent/

I can’t find the difference there. Should one of the layers be preferred in certain situations?

Answer 1

It seems to me that Masking () is more masking time steps; while Embedding (mask_zero = True) is more of a data filter. Disguise:

mask_value, timestep ()

mask_value. , , - , , .

, = 0. , , , . № 3 - , #i. , ( = ).

, , , , , ( = 0, 0 ), .