Neural network architecture in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple neural network layer using Keras.

ML Python

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

model = Sequential()
model.add(Dense([1], input_shape=(10,), activation='relu'))

Drag options to blanks, or click blank then click option'

ASequential

B'relu'

C10

D32

Attempts:

3 left

💡 Hint

Common Mistakes

Using the activation function name instead of the number of neurons.

Using the input shape as the number of neurons.

The first Dense layer needs the number of neurons as the first argument, here 32 neurons.

2fill in blank

medium

Complete the code to compile the model with the correct loss function for classification.

ML Python

model.compile(optimizer='adam', loss='[1]', metrics=['accuracy'])

Drag options to blanks, or click blank then click option'

Acategorical_crossentropy

Bmean_absolute_error

Cmean_squared_error

Dhinge

Attempts:

3 left

💡 Hint

Common Mistakes

Using mean squared error loss for classification.

Using hinge loss which is for SVMs.

For multi-class classification, 'categorical_crossentropy' is the correct loss function.

3fill in blank

hard

Fix the error in the code to add a dropout layer with 0.5 dropout rate.

ML Python

from tensorflow.keras.layers import Dropout

model.add(Dropout([1]))

Drag options to blanks, or click blank then click option'

A50

B0.5

C5

D1.5

Attempts:

3 left

💡 Hint

Common Mistakes

Using 50 instead of 0.5 for dropout rate.

Using values greater than 1.

Dropout rate should be a float between 0 and 1, so 0.5 means 50% dropout.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps layer names to their output shapes for layers with output shape length greater than 2.

ML Python

layer_shapes = {layer.name: layer.output_shape for layer in model.layers if len(layer.output_shape) [1] [2]

Drag options to blanks, or click blank then click option'

A>

B2

C<

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' in the condition.

Using 1 instead of 2 as the threshold.

We want layers where the output shape length is greater than 2, so use '>' and 2.

5fill in blank

hard

Fill all three blanks to create a dictionary that maps layer names in uppercase to their output shapes, but only for layers with output shape length greater than 1.

ML Python

layer_info = {layer.name[1]: layer.output_shape for layer in model.layers if len(layer.output_shape) [2] [3]

Drag options to blanks, or click blank then click option'

A.upper()

B>

C1

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Not using .upper() to convert names.

Using '<' instead of '>' in the condition.

Using 2 instead of 1 as the threshold.

We convert layer names to uppercase with .upper(), and filter layers with output shape length greater than 1.