A model summary is given below for neural network architecture.

Model: "sequential"

$\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_$

Layer $($type$)$ Output Shape Param #

$=================================================================$

dense$\_1($Dense$)($None$,64)($blank$)$

$\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_$

dense$\_2($Dense$)($None$,32)2080$

$\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_$

dense$\_3($Dense$)($None$,32)($blank$)$

$\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_$

dense$\_4($Dense$)($None$,5)($blank$)$

$=================================================================$

Total params: $($blank$)$

Trainable params: $($blank$)$

Non$-$trainable params: $0$

$\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_\_$

The input data vector has $1000$ features. The dense$\_4$ layer is the output layer.

Notice that there are blanks filled in different places. Let$$s answer a few questions to know each of the values.

Calculate the number of weights in the weight matrix for the first dense hidden layer.

$64000$

$32000$

$1000$

$64$