LSTM states $2$

$1$ point possible $($graded$)$

Now, we run the same model again with the same parameters and same initial conditions as in the previous question. The only difference is that

our input sequence in now: $1,1,0,1,1.$

Calculate the values $h_t$ at each time$-$step and enter them below as an array $h_0,h_1,h_2,h_3,h_4.$ Please round $h_t$ to the closest integer in every

time$-$step. For ease of calculation, we assume that sigmoid $(x)$~~$1$ and $tanh(x)$~~$1$ for $x1,$ and sigmoid$(x)$~~$0$ and $tanh(x)$~~$-1$

for $x-1.$

LSTM info

$\frac{1}{1}$ point $($graded$)$

What information is carried in the state $h_t?$

Whether the total number of zeros is odd.

Whether the number of consecutive zeros is odd.

Whether the total number of ones is odd.

Whether the number of consecutive ones is odd.