Time series with RNN in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing the right RNN layer for time series prediction

You want to predict future values of a time series using a recurrent neural network. Which TensorFlow layer is best suited to capture long-term dependencies in the data?

A tf.keras.layers.SimpleRNN

B tf.keras.layers.Conv1D

C tf.keras.layers.Dense

D tf.keras.layers.LSTM

💡 Hint

Think about which layer can remember information over many time steps.

LSTM layers are designed to remember information for long sequences, making them ideal for time series prediction where long-term dependencies matter.

❓ Predict Output

intermediate

Output shape of RNN layer

What is the output shape of the following TensorFlow code?

TensorFlow

import tensorflow as tf
model = tf.keras.Sequential([
    tf.keras.layers.LSTM(10, input_shape=(5, 3))
])
output_shape = model.output_shape

A (5, 10)

B (None, 5, 10)

C (None, 10)

D (None, 3)

💡 Hint

By default, LSTM returns the last output for each sample.

The LSTM layer with 10 units and input shape (5,3) returns output shape (None, 10) because it outputs the last time step's output for each batch sample.

❓ Hyperparameter

advanced

Effect of sequence length on RNN training

You train an RNN on time series data with sequences of length 100. You reduce the sequence length to 10. What is the most likely effect on training?

A Training will be faster but model may lose long-term context.

B Training will be slower and model will capture more context.

C Training speed and context capture remain unchanged.

D Training will be faster and model will capture more context.

💡 Hint

Shorter sequences mean less data per sample but less context.

Reducing sequence length speeds up training because the model processes fewer time steps, but it may lose important long-term dependencies in the data.

❓ Metrics

advanced

Choosing the right metric for time series regression

You train an RNN to predict continuous values in a time series. Which metric is best to evaluate the model's performance?

A Mean Squared Error (MSE)

B Categorical Crossentropy

C Accuracy

D Precision

💡 Hint

Think about metrics for continuous value prediction.

Mean Squared Error measures the average squared difference between predicted and true values, making it suitable for regression tasks like time series forecasting.

🔧 Debug

expert

Debugging exploding gradients in RNN training

You train an RNN on a long time series but notice the training loss becomes NaN after a few epochs. What is the most likely cause?

A Using Mean Squared Error instead of accuracy metric.

B Exploding gradients causing numerical instability.

C Incorrect input shape causing shape mismatch errors.

D Model underfitting due to too few layers.

💡 Hint

NaN loss often happens when gradients become too large.

Exploding gradients cause very large updates that make weights become NaN, leading to loss becoming NaN during training.

Practice

1. What is the main purpose of using an RNN (Recurrent Neural Network) in time series prediction?

easy

A. To learn patterns from past time steps to predict future values

B. To classify images into categories

C. To reduce the size of the dataset

D. To perform arithmetic operations on numbers

Solution

1. Step 1: Understand RNN's role in time series

   RNNs are designed to process sequences by remembering past information.

2. Step 2: Connect RNN to prediction task

   They use past time steps to predict future values in a sequence.

3. Final Answer:

   To learn patterns from past time steps to predict future values -> Option A

4. Quick Check:

   RNN predicts future from past [OK]

Hint: RNNs remember past data to predict next steps [OK]

Common Mistakes:

• Confusing RNN with image classifiers
• Thinking RNN reduces data size
• Assuming RNN does simple math only

2. Which of the following is the correct way to add a SimpleRNN layer with 50 units in TensorFlow Keras?

easy

A. model.add(tf.keras.layers.SimpleRNN(input_shape=(None, 1), 50))

B. model.add(tf.keras.layers.RNN(50))

C. model.add(tf.keras.layers.SimpleRNN(activation='relu', 50))

D. model.add(tf.keras.layers.SimpleRNN(units=50))

Solution

1. Step 1: Recall SimpleRNN syntax

   The units parameter must be named or passed first as an integer.

2. Step 2: Check each option

   model.add(tf.keras.layers.SimpleRNN(units=50)) uses named parameter units=50, which is correct and clear.

3. Final Answer:

   model.add(tf.keras.layers.SimpleRNN(units=50)) -> Option D

4. Quick Check:

   Use named units parameter [OK]

Hint: Use named 'units' parameter for clarity [OK]

Common Mistakes:

• Passing activation before units
• Omitting units parameter name
• Missing input_shape when required

3. Given this code snippet, what will be the shape of the output from the SimpleRNN layer?

model = tf.keras.Sequential()
model.add(tf.keras.layers.SimpleRNN(10, input_shape=(5, 2)))
output = model(tf.random.uniform((3, 5, 2)))
print(output.shape)

medium

A. (3, 2, 10)

B. (3, 10)

C. (5, 10)

D. (3, 5, 10)

Solution

1. Step 1: Understand input and output shapes

   Input shape is (batch=3, time steps=5, features=2). SimpleRNN with 10 units outputs (batch, units) by default.

2. Step 2: Confirm output shape

   Since return_sequences is False by default, output shape is (3, 10).

3. Final Answer:

   (3, 10) -> Option B

4. Quick Check:

   Default SimpleRNN outputs last step shape [OK]

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

Common Mistakes:

• Assuming output keeps time steps dimension
• Confusing batch size with time steps
• Misreading input_shape order

4. Identify the error in this TensorFlow RNN model code:

model = tf.keras.Sequential()
model.add(tf.keras.layers.SimpleRNN(20))
model.add(tf.keras.layers.Dense(1))
model.summary()
model.compile(optimizer='adam', loss='mse')
model.fit(x_train, y_train, epochs=5)

Assume x_train shape is (100, 10, 3).

medium

A. SimpleRNN layer missing input_shape parameter

B. Dense layer should have more units

C. Loss function 'mse' is invalid

D. Optimizer 'adam' is not supported

Solution

1. Step 1: Check input shape requirement

   First layer in Sequential must specify input_shape if no input layer is given.

2. Step 2: Verify code

   SimpleRNN(20) lacks input_shape=(10,3), so model won't know input dimensions.

3. Final Answer:

   SimpleRNN layer missing input_shape parameter -> Option A

4. Quick Check:

   First layer needs input_shape [OK]

Hint: Always specify input_shape in first RNN layer [OK]

Common Mistakes:

• Ignoring input_shape in first layer
• Changing Dense units unnecessarily
• Misunderstanding loss or optimizer names

5. You want to predict the next 3 values in a time series using an RNN. Which model setup is best to output a sequence of 3 predictions for each input sequence?

hard

A. Use SimpleRNN with return_sequences=True and a Dense layer with 3 units

B. Use SimpleRNN with return_sequences=False and a Dense layer with 3 units

C. Use SimpleRNN with return_sequences=True and a TimeDistributed Dense layer with 1 unit

D. Use SimpleRNN with return_sequences=False and a TimeDistributed Dense layer with 1 unit

Solution

1. Step 1: Understand output requirements

   Predicting next 3 values means outputting a sequence of length 3, one prediction per time step.

2. Step 2: Choose correct RNN and output layer

   return_sequences=True outputs a sequence (batch, time steps, units). A Dense layer with 3 units applied at each time step (via TimeDistributed) or a Dense layer with 3 units on the last step can be used depending on output shape.

3. Step 3: Analyze options

   Use SimpleRNN with return_sequences=True and a Dense layer with 3 units outputs only the last time step's output with 3 units, which is not a sequence of 3 predictions. Use SimpleRNN with return_sequences=True and a TimeDistributed Dense layer with 1 unit uses return_sequences=True and TimeDistributed Dense(1), producing a sequence output of shape (batch, time steps, 1), which can be adjusted to 3 time steps for 3 predictions.

4. Final Answer:

   Use SimpleRNN with return_sequences=True and a TimeDistributed Dense layer with 1 unit -> Option C

5. Quick Check:

   return_sequences=True + TimeDistributed Dense(1) outputs sequence predictions [OK]

Hint: return_sequences=True + TimeDistributed Dense(1) for sequence output [OK]

Common Mistakes:

• Using return_sequences=False for sequence output
• Using Dense without TimeDistributed for sequence output
• Misunderstanding output shapes