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.

Practice

1. Why are Recurrent Neural Networks (RNNs) especially good at processing sequential data like sentences or time series?

easy

A. Because they remember information from previous steps while processing new data

B. Because they process all data points independently without any memory

C. Because they use convolution to detect patterns in images

D. Because they only work with fixed-size input data

Solution

1. Step 1: Understand RNN memory feature

   RNNs keep track of past information by passing hidden states through time steps.

2. Step 2: Connect memory to sequential data

   This memory helps RNNs understand order and context in sequences like sentences or time series.

3. Final Answer:

   Because they remember information from previous steps while processing new data -> Option A

4. Quick Check:

   RNN memory = good for sequences [OK]

Hint: RNNs remember past inputs to handle sequences well [OK]

Common Mistakes:

• Thinking RNNs treat each input independently
• Confusing RNNs with convolutional networks
• Assuming RNNs only work with fixed-size data

2. Which of the following is the correct way to define a simple RNN layer in TensorFlow using Keras?

easy

A. tf.keras.layers.MaxPooling2D(pool_size=2)

B. tf.keras.layers.Dense(units=50)

C. tf.keras.layers.SimpleRNN(units=50)

D. tf.keras.layers.Conv2D(filters=50)

Solution

1. Step 1: Identify RNN layer syntax in TensorFlow

   The SimpleRNN layer is created with tf.keras.layers.SimpleRNN(units=...).

2. Step 2: Compare options to correct syntax

   Options A, B, and C are for other layer types (MaxPooling2D, Dense, Conv2D), not RNN.

3. Final Answer:

   tf.keras.layers.SimpleRNN(units=50) -> Option C

4. Quick Check:

   SimpleRNN layer syntax = tf.keras.layers.SimpleRNN(units=50) [OK]

Hint: SimpleRNN layer uses tf.keras.layers.SimpleRNN [OK]

Common Mistakes:

• Using Dense layer instead of RNN
• Confusing convolution layers with RNN
• Missing required units parameter

3. Consider this TensorFlow code snippet:

import tensorflow as tf
model = tf.keras.Sequential([
  tf.keras.layers.SimpleRNN(3, input_shape=(4, 2))
])
input_data = tf.constant([[[1.0, 2.0], [3.0, 4.0], [5.0, 6.0], [7.0, 8.0]]])
output = model(input_data)
print(output.numpy())

What is the shape of the output printed?

medium

A. (1, 3)

B. (4, 3)

C. (1, 4, 3)

D. (4, 2)

Solution

1. Step 1: Understand input and RNN output shapes

   Input shape is (batch=1, time=4, features=2). SimpleRNN with 3 units outputs (batch, units) by default.

2. Step 2: Confirm output shape without return_sequences

   Since return_sequences is False by default, output shape is (1, 3), one output per batch.

3. Final Answer:

   (1, 3) -> Option A

4. Quick Check:

   Output shape = (batch, units) = (1, 3) [OK]

Hint: Default SimpleRNN outputs last step shape (batch, units) [OK]

Common Mistakes:

• Assuming output shape includes time steps
• Confusing input shape with output shape
• Expecting 3D output without return_sequences=True

4. You wrote this code to create an RNN model:

model = tf.keras.Sequential([
  tf.keras.layers.SimpleRNN(5, input_shape=(None, 10))
])
model.compile(optimizer='adam', loss='mse')
model.fit(x_train, y_train, epochs=3)

But you get an error about input shape mismatch. What is the likely cause?

medium

A. SimpleRNN requires input_shape to be (10, None) instead

B. The optimizer 'adam' is not supported for RNNs

C. Loss 'mse' cannot be used with RNN models

D. x_train does not have 3 dimensions matching (batch, time, features)

Solution

1. Step 1: Check expected input shape for SimpleRNN

   SimpleRNN expects input shape (batch, time steps, features). The input_shape=(None, 10) means variable time steps, 10 features.

2. Step 2: Identify common input shape mismatch

   If x_train is missing the time dimension or has wrong shape, TensorFlow raises an error.

3. Final Answer:

   x_train does not have 3 dimensions matching (batch, time, features) -> Option D

4. Quick Check:

   Input shape mismatch = x_train does not have 3 dimensions matching (batch, time, features) [OK]

Hint: Check x_train shape matches (batch, time, features) [OK]

Common Mistakes:

• Blaming optimizer or loss for input shape errors
• Swapping time and feature dimensions in input_shape
• Using fixed time steps when variable allowed

5. You want to build an RNN in TensorFlow to predict the next word in a sentence. Which approach best uses RNNs' ability to process sequential data?

hard

A. Feed the entire sentence as one vector without sequence order

B. Feed the sentence word by word to the RNN, keeping track of hidden states

C. Use a convolutional layer to scan the sentence for word patterns

D. Shuffle the words randomly before feeding to the RNN

Solution

1. Step 1: Recall RNNs process sequences stepwise

   RNNs read inputs one step at a time, remembering past info via hidden states.

2. Step 2: Apply this to next word prediction

   Feeding words in order lets the RNN learn context to predict the next word accurately.

3. Final Answer:

   Feed the sentence word by word to the RNN, keeping track of hidden states -> Option B

4. Quick Check:

   Sequential input + memory = Feed the sentence word by word to the RNN, keeping track of hidden states [OK]

Hint: Feed words in order to keep context for prediction [OK]

Common Mistakes:

• Ignoring word order by feeding whole sentence as one vector
• Using convolution instead of RNN for sequence tasks
• Randomizing word order before input