Why RNNs process sequential data in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple RNN layer in TensorFlow.

TensorFlow

rnn_layer = tf.keras.layers.SimpleRNN([1], input_shape=(10, 8))

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

A32

Btf.keras.layers.SimpleRNN

CDense

Dactivation

Attempts:

3 left

💡 Hint

Common Mistakes

Using a layer type instead of a number for units.

Passing activation function as the first argument.

The number 32 specifies the number of units (neurons) in the RNN layer, which is required to create the layer.

2fill in blank

medium

Complete the code to compile the RNN model with an optimizer.

TensorFlow

model.compile(optimizer='[1]', loss='mse')

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

Asoftmax

Badam

Crelu

Daccuracy

Attempts:

3 left

💡 Hint

Common Mistakes

Using activation functions instead of optimizer names.

Using metrics like 'accuracy' as optimizer.

The optimizer 'adam' is commonly used for training RNNs and other neural networks.

3fill in blank

hard

Fix the error in the code to correctly reshape input data for the RNN.

TensorFlow

input_data = input_data.reshape(([1], 10, 8))

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

A10

B8

Cbatch_size

Dsequence_length

Attempts:

3 left

💡 Hint

Common Mistakes

Using sequence length or feature size as the first dimension.

Using fixed numbers instead of batch size variable.

The first dimension should be the batch size to match the model input requirements.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps each word to its length if the length is greater than 3.

TensorFlow

{word: [1] for word in words if [2] > 3}

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

Alen(word)

Bword

Dword.length

Attempts:

3 left

💡 Hint

Common Mistakes

Using word.length which is not valid in Python.

Using the word itself instead of its length.

We use len(word) to get the length of the word and check if it is greater than 3.

5fill in blank

hard

Fill all three blanks to create a dictionary that maps uppercase words to their lengths if length is greater than 4.

TensorFlow

{ [1]: [2] for word in words if [3] > 4 }

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

Aword.upper()

Blen(word)

Dword.lower()

Attempts:

3 left

💡 Hint

Common Mistakes

Using word.lower() instead of upper().

Using the word itself as the value instead of its length.

We convert the word to uppercase for the key, use len(word) for the value, and check if length is greater than 4.