A team is deploying a convolutional neural network for real-time object detection on a mobile device. The model currently has 50 million parameters and runs too slowly. The team needs to reduce the model size and latency. Which factor, if changed, would most directly reduce the model size?

Reduce the number of filters in the convolutional layers.

Increase the number of layers in the network.

Change the activation function from ReLU to tanh.

Increase the input image resolution.

In a deep neural network, what is a likely effect of increasing the number of layers?

The model requires less training data.

The model can learn more complex representations, but may be harder to train and more prone to overfitting.

The model always generalizes better to unseen data.

The model becomes faster to train.

AWSCertified Machine Learning Engineer - Associate

Domain 2Objective 2

Task 2.2: Train and Refine Models MLA-C01 Practice Questions (Page 3)

Part of the Content Domain 2: ML Model Development domain, which accounts for 26% of the MLA-C01 exam. AWS does not publish an official question count, but from its 130-minute exam (~50–85 total, ~13–22 in this domain), expect 4–7 from this objective — we provide 43 practice questions to prepare you well beyond it. (estimate)

43questions here

9free pages

16concepts

26%of the exam

16 Concepts in This Objective

Training process elements
Reducing training time
Factors influencing model size
Improving model performance
Regularization techniques
Hyperparameter tuning techniques
Model hyperparameters and effects
Integrating external models into SageMaker
SageMaker built-in algorithms and libraries
SageMaker script mode
Fine-tuning pre-trained models
SageMaker automatic model tuning
Preventing overfitting and underfitting
Ensembling and model combination
Reducing model size
Model version management

Questions 11–15

11foundation · easy
Which common ML library can be used within a SageMaker training job by providing a custom script?
Select an answer first
12foundation · easy
Which technique reduces model size by removing weights or neurons that contribute little to the model's output?
Select an answer first
13application · medium
A team is deploying a convolutional neural network for real-time object detection on a mobile device. The model currently has 50 million parameters and runs too slowly. The team needs to reduce the model size and latency. Which factor, if changed, would most directly reduce the model size?
Select an answer first
14foundation · easy
Which of the following is an example of a SageMaker built-in algorithm?
Select an answer first
15foundation · easy
In a deep neural network, what is a likely effect of increasing the number of layers?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to MLA-C01

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by AWS. “MLA-C01” is a trademark of its owner, used for identification only.

Task 2.2: Train and Refine Models MLA-C01 Practice Questions (Page 3)

Questions 11–15

Which common ML library can be used within a SageMaker training job by providing a custom script?

Which technique reduces model size by removing weights or neurons that contribute little to the model's output?

A team is deploying a convolutional neural network for real-time object detection on a mobile device. The model currently has 50 million parameters and runs too slowly. The team needs to reduce the model size and latency. Which factor, if changed, would most directly reduce the model size?

Which of the following is an example of a SageMaker built-in algorithm?

In a deep neural network, what is a likely effect of increasing the number of layers?

Keep studying — Content Domain 2: ML Model Development