Weights from Input to First Hidden Layer:

$W_1=\left[\begin{array}{ccc}0\mathrm{.}1& 0\mathrm{.}2& 0\mathrm{.}3\\ 0\mathrm{.}4& 0\mathrm{.}5& 0\mathrm{.}6\\ 0\mathrm{.}7& 0\mathrm{.}8& 0\mathrm{.}9\\ 0\mathrm{.}1& 0\mathrm{.}2& 0\mathrm{.}3\end{array}\right],b_1=\left[\begin{array}{c}0\mathrm{.}1\\ 0\mathrm{.}2\\ 0\mathrm{.}3\\ 0\mathrm{.}4\end{array}\right]$

Weights from First Hidden Layer to Second Hidden Layer:

$W_2=\left[\begin{array}{cccc}0\mathrm{.}1& 0\mathrm{.}2& 0\mathrm{.}3& 0\mathrm{.}4\\ 0\mathrm{.}5& 0\mathrm{.}6& 0\mathrm{.}7& 0\mathrm{.}8\\ 0\mathrm{.}9& 0\mathrm{.}1& 0\mathrm{.}2& 0\mathrm{.}3\\ 0\mathrm{.}4& 0\mathrm{.}5& 0\mathrm{.}6& 0\mathrm{.}7\end{array}\right],b_2=\left[\begin{array}{c}0\mathrm{.}1\\ 0\mathrm{.}2\\ 0\mathrm{.}3\\ 0\mathrm{.}4\end{array}\right]$

Weights from Second Hidden Layer to Output Layer:

$W_3=\left[\begin{array}{cccc}0\mathrm{.}1& 0\mathrm{.}2& 0\mathrm{.}3& 0\mathrm{.}4\end{array}\right],b_3=0\mathrm{.}1$

$,S(x)=\frac{1}{1+e^{-x}}$

Sigmoid Function is used as the activation function.

$w(n+1)=w(n)+a**w(n-1)+**(n)**y$;$,(=0$;$=00\mathrm{.}1)$

According to the Input vector $x=[1,2,3],$ output value is expected to be $0\mathrm{.}8.$

Calculate the output according to these weights $($Input vector $x=[1,2,3],$ expected output$=0\mathrm{.}8).$

Caculate the error

Use backpropogation algorithms to update the weights, SHOW the weights.

Calculate the output value according to these weights $($Input vector $x=[1,2,3],$ expected output$=0\mathrm{.}8).$

Caculate the error

Is there any decrease in the error amount. Explain your answer.

SHOW ALL YOUR CALCULATION WITH YOUR OWN HANDWRITING