A neural network designed using Tensorflow Keras is given below.

net $=$ t f $.$ ke ras $.$ l a y e r s $.$ Se quent i a l $()$

net $.$ add $($

t f $.$ ke ras $.$ l a y e r s $.$ InputLayer $($ input$\_$shape $=((256*256*3),)),$

t f $.$ ke ras $.$ l a y e r s $.$ Dense $(1048,$ a c t i v a t i o n$=$ r e lu $),$

t f $.$ ke ras $.$ l a y e r s $.$ Dense $(512,$ a c t i v a t i o n$=$ r e lu $),$

t f $.$ ke ras $.$ l a y e r s $.$ Dropout $(0.4),$

t f $.$ ke ras $.$ l a y e r s $.$ Dense $(256,$ a c t i v a t i o n$=$ r e lu $),$

t f $.$ ke ras $.$ l a y e r s $.$ Dense $(128,$ a c t i v a t i o n$=$ r e lu $),$

t f $.$ ke ras $.$ l a y e r s $.$ Dense $(64,$ a c t i v a t i o n$=$ r e lu $),$

t f $.$ ke ras $.$ l a y e r s $.$ Dropout $(0.6),$

t f $.$ ke ras $.$ l a y e r s $.$ Dense $(32,$ a c t i v a t i o n$=$ r e lu $),$

t f $.$ ke ras $.$ l a y e r s $.$ Dense $(16,$ a c t i v a t i o n$=$ r e lu $),$

t f $.$ ke ras $.$ l a y e r s $.$ Dense $(8,$ a c t i v a t i o n$=$softmax $))$

$($a$)$ What is the objective of the neural network? What is the input given to the network?

What is the expected output? How deep and wide is the network. $[2]$

$($b$)$ Justify the choice activation function in output layer. Instead of Relu activation function,

justify the choice of using Tanh activation function. $[1]$

$($c$)$ Two dropout statements are added in the code. How many additional parameters are

learned because of this? If drop out is added after the last statement in the given code,

how will it affect the network? $[1]$

$($d$)$ Write the code snippet for adding the optimizer of your choice. Justify the choice of

the optimizer. Assume any other relevant information. $[1]$

$($e$)$ What will the following code snippet do to the network. $[1]$

cb $=$ t f $.$ ke ras $.$ c a l l b a c k s $.$ EarlyStopping $($monitor$=$ l o s s $,$ pa t i enc e$=7)$

h i s t o r y $=$ net $.$ f i t $($ epochs$=200,$ batch$\_$size$=32,$ c a l l b a c k s $=[$cb $])$ for above program