Transformer modeling in Simulink - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define the input layer for a transformer model in Simulink.

Simulink

inputLayer = sequenceInputLayer([1]);

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

A256

B512

C1024

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing a size that does not match the embedding dimension.

Confusing sequence length with embedding size.

The input layer size is typically set to the embedding dimension, which is 128 in this example.

2fill in blank

medium

Complete the code to add a multi-head attention layer with 8 heads in Simulink.

Simulink

multiHeadAttn = multiHeadAttentionLayer([1], 'Name', 'multiHeadAttn');

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

A8

B4

C16

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Using too few or too many heads without adjusting other parameters.

Confusing number of heads with embedding size.

Transformers commonly use 8 attention heads for multi-head attention layers.

3fill in blank

hard

Fix the error in the code to correctly add a position-wise feedforward layer in Simulink.

Simulink

feedForward = fullyConnectedLayer([1], 'Name', 'feedForward');

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

A512

B2048

C256

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Using the embedding size instead of the larger feedforward size.

Choosing a size too small to capture complex features.

The feedforward layer in transformers typically has a larger size, often 2048, to increase model capacity.

4fill in blank

hard

Fill both blanks to correctly create a transformer encoder block with normalization and dropout layers.

Simulink

encoderBlock = [layerNormalizationLayer('Name', 'norm1'), dropoutLayer([1], 'Name', 'dropout1'), layerNormalizationLayer('Name', 'norm2'), dropoutLayer([2], 'Name', 'dropout2')];

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

A0.1

B0.2

C0.3

D0.4

Attempts:

3 left

💡 Hint

Common Mistakes

Using dropout rates that are too high, causing underfitting.

Using different dropout rates for the two dropout layers.

Dropout rates of 0.1 are commonly used in transformer encoder blocks to prevent overfitting.

5fill in blank

hard

Fill all three blanks to define the transformer model layers including input, encoder, and output layers.

Simulink

layers = [sequenceInputLayer([1], 'Name', 'input'), transformerEncoderLayer([2], [3], 'Name', 'encoder'), fullyConnectedLayer(10, 'Name', 'output')];

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

A128

B8

C2048

D256

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up the order of parameters in the encoder layer.

Using inconsistent sizes that don't match transformer architecture.

The input size is 128, the encoder uses 8 attention heads, and the feedforward dimension is 2048, matching common transformer settings.

Practice

1. What is the main purpose of the attention mechanism in a Transformer model in Simulink?

easy

A. To focus on important parts of the input sequence

B. To increase the size of the input data

C. To reduce the number of layers in the model

D. To convert sequence data into images

Solution

1. Step 1: Understand the role of attention in Transformers

   The attention mechanism helps the model decide which parts of the input sequence are most important for making predictions.

2. Step 2: Relate attention to sequence processing in Simulink

   In Simulink, attention blocks highlight key sequence elements, improving model focus and accuracy.

3. Final Answer:

   To focus on important parts of the input sequence -> Option A

4. Quick Check:

   Attention = Focus on important parts [OK]

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

Common Mistakes:

• Thinking attention changes input size
• Confusing attention with layer count
• Assuming attention converts data types

2. Which Simulink block is typically used to implement the multi-head attention mechanism in a Transformer model?

easy

A. Multiport Switch block

B. Multi-Head Attention block

C. MATLAB Function block

D. Sum block

Solution

1. Step 1: Identify the block for multi-head attention

   Simulink provides a dedicated Multi-Head Attention block designed to implement this mechanism efficiently.

2. Step 2: Compare with other blocks

   Sum and Multiport Switch blocks do not perform attention; MATLAB Function block requires custom code.

3. Final Answer:

   Multi-Head Attention block -> Option B

4. Quick Check:

   Multi-Head Attention block = Correct block [OK]

Hint: Look for block named 'Multi-Head Attention' [OK]

Common Mistakes:

• Choosing generic blocks like Sum or Switch
• Assuming MATLAB Function block is default for attention
• Confusing block names

3. Given this Simulink Transformer model snippet, what will be the output shape after the multi-head attention block if the input sequence has shape (batch=2, length=10, features=64) and the block uses 8 heads each with 8 features?

medium

A. (2, 10, 64)

B. (2, 8, 64)

C. (2, 10, 8)

D. (2, 64, 10)

Solution

1. Step 1: Understand multi-head attention output shape

   The output shape matches the input sequence shape: batch size and sequence length stay the same, features remain 64.

2. Step 2: Confirm feature dimension calculation

   8 heads x 8 features per head = 64 features total, so output features = 64.

3. Final Answer:

   (2, 10, 64) -> Option A

4. Quick Check:

   Output shape = Input shape [OK]

Hint: Output shape matches input shape in multi-head attention [OK]

Common Mistakes:

• Multiplying batch or length by heads
• Confusing feature dimension with head count
• Swapping sequence length and feature dimensions

4. You built a Transformer model in Simulink but get an error: 'Dimension mismatch in matrix multiplication'. What is the most likely cause?

medium

A. Input sequence length is zero

B. Batch size is too large

C. Feature dimensions between layers do not match

D. Using wrong activation function

Solution

1. Step 1: Analyze the error message

   Dimension mismatch in matrix multiplication usually means the number of columns in one matrix does not match the number of rows in the next.

2. Step 2: Relate to Transformer layers in Simulink

   If feature dimensions between connected layers differ, matrix multiplication fails causing this error.

3. Final Answer:

   Feature dimensions between layers do not match -> Option C

4. Quick Check:

   Dimension mismatch = Feature size mismatch [OK]

Hint: Check feature sizes between connected blocks [OK]

Common Mistakes:

• Blaming batch size for dimension errors
• Ignoring feature dimension compatibility
• Assuming activation function causes dimension errors

5. You want to improve your Transformer model in Simulink to better predict sequences with long-range dependencies. Which change is most effective?

hard

A. Use fewer Transformer layers

B. Reduce the sequence length input

C. Replace attention with convolution blocks

D. Increase the number of attention heads

Solution

1. Step 1: Understand long-range dependency handling

   More attention heads allow the model to focus on multiple parts of the sequence simultaneously, capturing long-range relationships better.

2. Step 2: Evaluate other options

   Reducing sequence length or layers limits model capacity; replacing attention with convolution loses global context.

3. Final Answer:

   Increase the number of attention heads -> Option D

4. Quick Check:

   More heads = Better long-range focus [OK]

Hint: More attention heads capture more sequence details [OK]

Common Mistakes:

• Thinking fewer layers improve performance
• Reducing sequence length helps long-range learning
• Replacing attention with convolution is better