Why RNNs handle sequences in PyTorch - Challenge Your Understanding

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why do RNNs remember previous inputs?

Recurrent Neural Networks (RNNs) are special because they can remember information from earlier in a sequence. Why is this possible?

A Because RNNs treat each input independently without sharing information.

B Because RNNs have loops that pass information from one step to the next in the sequence.

C Because RNNs use random noise to guess previous inputs.

D Because RNNs use convolution layers to scan the entire sequence at once.

💡 Hint

Think about how RNNs connect one step to the next in a sequence.

RNNs have loops in their structure that allow information to flow from one time step to the next, helping them remember past inputs.

❓ Predict Output

intermediate

Output shape of RNN with sequence input

Consider this PyTorch code snippet creating an RNN and passing a batch of sequences through it. What is the shape of the output tensor?

PyTorch

import torch
import torch.nn as nn

rnn = nn.RNN(input_size=5, hidden_size=3, num_layers=1, batch_first=True)
input_seq = torch.randn(4, 7, 5)  # batch=4, seq_len=7, input_size=5
output, hidden = rnn(input_seq)
print(output.shape)

A torch.Size([4, 7, 3])

B torch.Size([7, 4, 3])

C torch.Size([4, 3, 7])

D torch.Size([3, 4, 7])

💡 Hint

Remember that batch_first=True means batch size is the first dimension.

The output shape is (batch_size, sequence_length, hidden_size) when batch_first=True.

❓ Model Choice

advanced

Choosing RNN for sequence data

You want to build a model that predicts the next word in a sentence. Which model type is best suited to handle the sequence nature of this task?

A A clustering algorithm that groups similar words.

B A feedforward neural network that treats each word independently.

C A convolutional neural network that scans fixed-size windows of words.

D A recurrent neural network that processes words one by one and remembers previous words.

💡 Hint

Think about which model can remember previous words in a sentence.

RNNs are designed to handle sequences by processing inputs step-by-step and keeping track of past information, making them ideal for predicting the next word.

❓ Hyperparameter

advanced

Effect of hidden size in RNNs

In an RNN, what is the effect of increasing the hidden_size parameter?

A It increases the number of features the RNN can remember at each step, allowing it to capture more complex patterns.

B It reduces the sequence length the RNN can process.

C It changes the input size of the RNN to accept larger vectors.

D It decreases the number of layers in the RNN.

💡 Hint

Think about what hidden_size controls inside the RNN cell.

The hidden_size controls the size of the hidden state vector, which stores information from previous steps. Larger hidden_size means more capacity to learn complex patterns.

❓ Metrics

expert

Evaluating sequence prediction with RNN

You trained an RNN to predict the next character in a text sequence. After training, you want to measure how well it predicts. Which metric is most appropriate to evaluate this task?

A Mean squared error between predicted and true characters encoded as numbers.

B Silhouette score measuring cluster separation.

C Accuracy of predicted characters compared to true next characters.

D Confusion matrix of predicted vs true sentence lengths.

💡 Hint

Think about what it means to predict the next character correctly.

Accuracy measures how often the predicted character matches the true next character, which is the right metric for classification tasks like next character prediction.