Why attention revolutionized deep learning in PyTorch - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple attention score using dot product.

PyTorch

import torch

query = torch.tensor([[1, 0, 1]], dtype=torch.float32)
key = torch.tensor([[0, 1, 0]], dtype=torch.float32)

attention_score = torch.matmul(query, [1].T)
print(attention_score)

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

Akey

Bquery

Ctorch.tensor([[1, 1, 1]])

Dtorch.eye(3)

Attempts:

3 left

💡 Hint

Common Mistakes

Using query instead of key for the dot product.

Not transposing the key tensor before multiplication.

The attention score is calculated by the dot product of the query and the transpose of the key.

2fill in blank

medium

Complete the code to apply softmax to the attention scores.

PyTorch

import torch
import torch.nn.functional as F

scores = torch.tensor([[1.0, 2.0, 3.0]])
attention_weights = F.[1](scores, dim=1)
print(attention_weights)

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

Asigmoid

Brelu

Csoftmax

Dtanh

Attempts:

3 left

💡 Hint

Common Mistakes

Using sigmoid which does not normalize across the dimension.

Using relu or tanh which do not produce probability distributions.

Softmax converts raw scores into probabilities that sum to 1, which is essential for attention weights.

3fill in blank

hard

Fix the error in the scaled dot-product attention calculation.

PyTorch

import torch
import math

query = torch.randn(1, 4)
key = torch.randn(1, 4)
scale = math.sqrt(query.shape[1])
scores = torch.matmul(query, key.T) / [1]
print(scores)

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

Aquery.shape[0]

Bkey.shape[1]

Ckey.shape[0]

Dquery.shape[1]

Attempts:

3 left

💡 Hint

Common Mistakes

Using batch size dimension instead of feature dimension for scaling.

Using key shape dimension incorrectly.

The scale factor is the square root of the key/query dimension, which is query.shape[1].

4fill in blank

hard

Fill both blanks to complete the attention output calculation.

PyTorch

import torch
import torch.nn.functional as F

query = torch.randn(1, 3)
key = torch.randn(1, 3)
value = torch.randn(1, 3)

scores = torch.matmul(query, key.T) / torch.sqrt(torch.tensor(query.shape[[1]], dtype=torch.float32))
weights = F.softmax(scores, dim=[2])
output = torch.matmul(weights, value)
print(output)

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

A1

B0

C2

D-1

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong shape index for scaling.

Applying softmax on wrong dimension.

The feature dimension is at index 1 for shape, and softmax is applied along dimension 0 for batch size.

5fill in blank

hard

Fill all three blanks to implement a simple attention mechanism output.

PyTorch

import torch
import torch.nn.functional as F

query = torch.randn(2, 4)
key = torch.randn(2, 4)
value = torch.randn(2, 4)

scores = torch.matmul(query, key.T) / torch.sqrt(torch.tensor(query.shape[[1]], dtype=torch.float32))
weights = F.softmax(scores, dim=[2])
attention_output = torch.matmul(weights, [3])
print(attention_output)

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

A1

B0

Cvalue

Dkey

Attempts:

3 left

💡 Hint

Common Mistakes

Using key instead of value for final multiplication.

Incorrect dimension indices for scaling or softmax.

Scale by feature dimension (index 1), apply softmax along batch dimension (0), and multiply weights by value to get output.

Practice

1. What is the main reason attention mechanisms changed deep learning models?

easy

A. They make models run faster on CPUs.

B. They reduce the size of the training data needed.

C. They let models focus on important parts of the input data.

D. They remove the need for any training.

Solution

1. Step 1: Understand attention's role

   Attention helps models decide which parts of the input are most important to look at.

2. Step 2: Compare options

   Only They let models focus on important parts of the input data. correctly states this key benefit; others are incorrect or unrelated.

3. Final Answer:

   They let models focus on important parts of the input data. -> Option C

4. Quick Check:

   Attention = Focus on important data [OK]

Hint: Attention means focusing on key input parts [OK]

Common Mistakes:

• Thinking attention reduces training data size
• Believing attention speeds up CPU processing
• Assuming attention removes training need

2. Which PyTorch code snippet correctly creates a simple attention layer using nn.MultiheadAttention?

easy

A. attn = nn.MultiheadAttention(embed_dim=64, num_heads=8)

B. attn = nn.MultiheadAttention(num_heads=64, embed_dim=8)

C. attn = nn.MultiheadAttention(8, 64)

D. attn = nn.MultiheadAttention(embed_dim=8, num_heads=64)

Solution

1. Step 1: Check PyTorch docs for nn.MultiheadAttention

   The correct order is embed_dim first, then num_heads as named arguments.

2. Step 2: Validate options

   Only attn = nn.MultiheadAttention(embed_dim=64, num_heads=8) uses correct argument names and values; others swap values between embed_dim and num_heads or use positional arguments incorrectly.

3. Final Answer:

   attn = nn.MultiheadAttention(embed_dim=64, num_heads=8) -> Option A

4. Quick Check:

   embed_dim first, num_heads second [OK]

Hint: Remember embed_dim before num_heads in nn.MultiheadAttention [OK]

Common Mistakes:

• Swapping embed_dim and num_heads
• Using positional args in wrong order
• Confusing parameter names

3. Given this PyTorch code using attention, what is the shape of the output tensor?

import torch
import torch.nn as nn

attn = nn.MultiheadAttention(embed_dim=16, num_heads=4)
query = torch.rand(5, 3, 16)  # (seq_len, batch, embed_dim)
key = torch.rand(5, 3, 16)
value = torch.rand(5, 3, 16)
out, weights = attn(query, key, value)
print(out.shape)

medium

A. (3, 16, 5)

B. (5, 3, 16)

C. (16, 3, 5)

D. (3, 5, 16)

Solution

1. Step 1: Understand input shapes for nn.MultiheadAttention

   Inputs are (seq_len, batch_size, embed_dim). Output shape matches query shape.

2. Step 2: Check given query shape

   Query shape is (5, 3, 16), so output shape is the same.

3. Final Answer:

   (5, 3, 16) -> Option B

4. Quick Check:

   Output shape = query shape = (5, 3, 16) [OK]

Hint: Output shape matches query shape in MultiheadAttention [OK]

Common Mistakes:

• Mixing batch and sequence dimensions
• Confusing embed_dim position
• Assuming output shape changes

4. This PyTorch code throws an error. What is the mistake?

import torch
import torch.nn as nn

attn = nn.MultiheadAttention(embed_dim=32, num_heads=4)
query = torch.rand(10, 2, 16)
key = torch.rand(10, 2, 16)
value = torch.rand(10, 2, 16)
out, weights = attn(query, key, value)

medium

A. Number of heads must be 16

B. Batch size must be first dimension

C. Query, key, value must be 2D tensors

D. embed_dim in MultiheadAttention does not match input embed_dim

Solution

1. Step 1: Check embed_dim consistency

   MultiheadAttention expects input embed_dim to match embed_dim parameter (32), but inputs have embed_dim=16.

2. Step 2: Confirm input shape format

   Input shape (seq_len, batch, embed_dim) is correct, batch is second dimension, so no error there.

3. Final Answer:

   embed_dim in MultiheadAttention does not match input embed_dim -> Option D

4. Quick Check:

   embed_dim mismatch causes error [OK]

Hint: embed_dim must match between layer and inputs [OK]

Common Mistakes:

• Mixing batch and sequence dimensions
• Ignoring embed_dim mismatch
• Expecting 2D tensors instead of 3D

5. Why did attention mechanisms especially revolutionize natural language processing (NLP) compared to older models?

hard

A. Because attention allows models to weigh all words in a sentence dynamically, capturing context better.

B. Because attention removes the need for any word embeddings.

C. Because attention makes models ignore word order completely.

D. Because attention reduces the number of layers needed to one.

Solution

1. Step 1: Understand attention's effect on context in NLP

   Attention lets models look at all words and decide which are important for each output word, capturing context dynamically.

2. Step 2: Evaluate options

   Because attention allows models to weigh all words in a sentence dynamically, capturing context better. correctly describes this. The other options are incorrect: attention still requires word embeddings; it preserves word order via positional encodings; it does not reduce the number of layers to one.

3. Final Answer:

   Because attention allows models to weigh all words in a sentence dynamically, capturing context better. -> Option A

4. Quick Check:

   Attention = dynamic context weighting [OK]

Hint: Attention captures context by weighing all words [OK]

Common Mistakes:

• Thinking attention removes embeddings
• Believing attention ignores word order
• Assuming attention reduces layers to one