SimpleRNN layer in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a SimpleRNN layer with 50 units.

TensorFlow

from tensorflow.keras.layers import SimpleRNN
rnn_layer = SimpleRNN([1])

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

A50

B10

C100

D5

Attempts:

3 left

💡 Hint

Common Mistakes

Using a number too small or too large without reason.

Forgetting to specify the number of units.

The SimpleRNN layer requires the number of units as the first argument. Here, 50 units are specified.

2fill in blank

medium

Complete the code to add a SimpleRNN layer to a Sequential model.

TensorFlow

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import SimpleRNN
model = Sequential()
model.add(SimpleRNN([1], input_shape=(10, 8)))

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

A8

B32

C16

D64

Attempts:

3 left

💡 Hint

Common Mistakes

Not specifying input_shape in the first layer.

Choosing a number of units that is too small or too large.

The SimpleRNN layer is added with 32 units and an input shape of 10 time steps and 8 features.

3fill in blank

hard

Fix the error in the SimpleRNN layer creation by completing the code.

TensorFlow

from tensorflow.keras.layers import SimpleRNN
rnn = SimpleRNN(units=[1], return_sequences=True)

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

A20

B'20'

CNone

DTrue

Attempts:

3 left

💡 Hint

Common Mistakes

Passing units as a string instead of an integer.

Using invalid types like None or True for units.

The units argument must be an integer, not a string or other type. 20 is a valid integer.

4fill in blank

hard

Fill both blanks to create a SimpleRNN layer that returns sequences and uses tanh activation.

TensorFlow

rnn_layer = SimpleRNN([1], activation=[2], return_sequences=True)

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

A40

B'relu'

C'tanh'

D30

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'relu' instead of 'tanh' for activation.

Not setting return_sequences=True when needed.

The layer has 40 units and uses 'tanh' activation, which is the default for SimpleRNN.

5fill in blank

hard

Fill all three blanks to build a Sequential model with a SimpleRNN layer followed by a Dense output layer.

TensorFlow

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import SimpleRNN, Dense
model = Sequential([
    SimpleRNN([1], input_shape=(15, 10), activation=[2]),
    Dense([3], activation='softmax')
])

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

A64

B'relu'

C5

D32

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up the order of layers.

Using wrong activation functions.

Incorrect output size in Dense layer.

The SimpleRNN layer has 32 units with 'relu' activation, and the Dense layer outputs 5 classes with softmax.