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.