model $=$ models. Sequential$()$ # Layer $1$ model.add $($layers$.$ Dense $(50,$ activation$=$'relu', input # Layer $2$ model.add$($layers$.$ Dense $(40,$ activation$=$'relu'$))$ # Layer $3$ model.add$($layers$.$Dense $(30,$ activation$=$'relu'$))$ # Layer $4.$ model.add$($layers$.$ Dense $(**$B$**,$ activation$=**$C$**))$ model.compile $($optimizer $\text{'}$sgd$\text{'},$ loss $=**$D$**,$ metri $\text{'}])$ A$.$ What is the input shape $**$A$**$ in Layer $1?(32*32*3,)$ or $(3072)$ B$.$ What will be the value of $**$B$**,$ activation function $**$C$**$ and loss total number of classes in the dataset is i$.21,$ sigmoid, binary$\_$crossentropy $11.1010,$ softmax, categorical$\_$crossentropyA. Consider the MLP below where each perceptron has a linear activation function where the output z is related to its inputs x and y as z $=$ ax $+$ by $+$ c$.$ We claim that this network can be replaced by a single perceptron with a possibly different linear activation function. Is this claim true or not? Give quantitative justification for your answer. $$ B$.$ We would like to minimize the following quadratic function $0\mathrm{.}5\mathrm{.}25$x$2+16*$x $+12$ using exactly two steps using gradient$-$descent with a learning rate n $-10$ for the first step. What should the learning rate of the second$-$step be in order to obtain the minimum in two$-$steps? $13+3-6$ Marks