A neural network has a structure as shown in Figure below, assuming that all the activation functions are sigmoid.

a$.$ Explain briefly how neural networks differ from conventional computing.

b$.$ What are the neural networks limitations$?$

c$.$ Calculate the values of $y_{12}$ and $y_{22}$ when the input are $x_1=0\mathrm{.}3,x_2=0\mathrm{.}5,$ when the weights and biases are:

Hidden layer

Output layer

d$.$ Find the values of $y_{12}$ and $y_{22}$ when the input are $x_1=0\mathrm{.}9,x_2=0\mathrm{.}1,$ all activation functions are digital bi$-$polar, and use the same weights as in $3$ above.

e$.$ Write a MATLAB program to evaluate the output $y_{12}$ and $y_{22}.$

f$.$ It should be submitted in a form of a report.

g $.$ The report to be presented in power point in the class room in front of classmate.