(Choose 1 answer)
Here are the equations for the GRU and the LSTM:
From these, we can see that the Update Gate and Forget Gate in the LSTM play a role similar to and in the GRU. What should go in the the blanks?
A. Γrand Tu
B. Tu and Fr
C. 1-Γu and ru
D. Γu and 1-Ги
GRU
<t> = tanh(W[rc<t-1>, x<t>] +bc)
Tu = (Wu [c<-1>, x<t>] + bu)
Γ, σ(W,[c<-1>, x<t>] + br)
c<t> = <t> + (1) c<-1>
a<t> = <t>
LSTM
x<t>] +bc)<t> = tanh(We[a<t-1>, x<t
<t>] + bu)Γα = σ(W[α<-1>,x<t>]
1>, x<t>] + by)Γ = (W, [a<-1>, x<t>]
To = (Wo [a<-1>, x<x<t>] + bo)
c<t> = Tu * <t> + [ * c<t-1>
a<t> = loc<t>
Exit 29
