This question asks you to use a Python notebook to answer.

Using this ipy Download Using this ipy, answer the below.

You are building a neural network using the following layers:

A dense layer with $512$ units with an input shape of max$\_$words.

A ReLU activation function

A dropout rate of $0\mathrm{.}5$

Another dense layer with num$\_$classes units

A final activation function with softmax

The network is compiled with categorical cross$-$entropy as the loss function, the Adam optimizer, and accuracy as an evaluation metric.

Hint:

model.compile$($loss$=$'categorical$\_$crossentropy',

optimizer$=$'adam',

metrics$=[\text{'}$accuracy$\text{'}])$

model.summary$()$

What is the total number of parameters in this neural network?

Please enter your answer as a numeric value. max$\_$words $=1000$

batch$\_$size $=32$

epochs $=5$

print$(\text{'}$Loading data...$\text{'})$

$($x$\_$train, y$\_$train$),($x$\_$test, y$\_$test$)=$ reuters.load$\_$data$($num$\_$words$=$max$\_$words,

test$\_$split$=0\mathrm{.}2)$

print$($len$($x$\_$train$),$ 'train sequences'$)$

print$($len$($x$\_$test$),$ 'test sequences'$)$

num$\_$classes $=$ np$.$max$($y$\_$train$)+1$

print$($num$\_$classes, 'classes'$)$

print$(\text{'}$Vectorizing sequence data...$\text{'})$

tokenizer $=$ Tokenizer$($num$\_$words$=$max$\_$words$)$

x$\_$train $=$ tokenizer.sequences$\_$to$\_$matrix$($x$\_$train, mode$=$'binary'$)$

x$\_$test $=$ tokenizer.sequences$\_$to$\_$matrix$($x$\_$test, mode$=$'binary'$)$

print$(\text{'}$x$\_$train shape:$\text{'},$ x$\_$train.shape$)$

print$(\text{'}$x$\_$test shape:$\text{'},$ x$\_$test.shape$)$

print$(\text{'}$Convert class vector to class matrix $\text{'}$

$\text{'}($for use with categorical$\_$crossentropy$)\text{'})$

y$\_$train $=$ tf$.$keras.utils.to$\_$categorical$($y$\_$train, num$\_$classes$)$

y$\_$test $=$ tf$.$keras.utils.to$\_$categorical$($y$\_$test, num$\_$classes$)$

print$(\text{'}$y$\_$train shape:$\text{'},$ y$\_$train.shape$)$

print$(\text{'}$y$\_$test shape:$\text{'},$ y$\_$test.shape$)$