This will initially boost ¯H relative to ¯S because it will suddenly be joined to a network with is correctly transmitting ¯H but which does not understand ¯S at all.
However, as these networks are trained to equilibrium the advantage will disappear as a steganographic protocol is agreed between the two models. Also, this can only be used once before the networks are in equilibrium.
Why would it be desirable to do this end-to-end training at all, rather than simply sticking the two networks together and doing no further training? Also, can you clarify what the last sentence means? (I have guesses, but I’d rather just know what you meant)
Why would it be desirable to do this end-to-end training at all, rather than simply sticking the two networks together and doing no further training? Also, can you clarify what the last sentence means?
(I have guesses, but I’d rather just know what you meant)