This feedforward Neural network has an input layer, a hidden layer, and an output layer. There

are two input units, three hidden units, and one output unit. The input training data is $1$ and $1.$ The

target output is $1.$ The activation function is a Sigmoid function. The learning rate is $0\mathrm{.}5.$

Compute to change the given connection weights by backpropagation algorithm. Show the

process of your computation.

The weights are given as

between input unit $1$ and hidden unit $1$ is $0\mathrm{.}9$

between input unit $1$ and hidden unit $2$ is $0\mathrm{.}8$

between input unit $1$ and hidden unit $3$ is $0\mathrm{.}7$

between input unit $2$ and hidden unit $1$ is $0\mathrm{.}6$

between input unit $2$ and hidden unit $2$ is $0\mathrm{.}5$

between input unit $2$ and hidden unit $3$ is $0\mathrm{.}4$

between hidden unit $1$ and output unit $1$ is $0\mathrm{.}3$

between hidden unit $2$ and output unit $1$ is $0\mathrm{.}2$

between hidden unit $3$ and output unit $1$ is $0\mathrm{.}1$

Your answer should be rounded $3$ decimal places. For example, if the number is $0\mathrm{.}12345,$ then it

would be $0\mathrm{.}123.$ If the number is $0\mathrm{.}12354,$ then it would be $0\mathrm{.}124.$

$(2-1)$ What is the actual output of Hidden unit $3?$

$(2-2)$ What is the actual output of Output unit $1?$

$(2-3)$ What is the updated weight of $0\mathrm{.}2?$

$(2-4)$ What is the delta of Hidden unit $3?$

$(2-5)$ What is the updated weight of $0\mathrm{.}6?$