- A
L2 regularization on weights
L2 regularization penalizes large weights, helping generalization.
- B
Increase the number of layers in the network
Why wrong: Adding layers increases model complexity, likely worsening overfitting.
- C
Data augmentation (e.g., random crops, flips)
Augmentation increases effective training data size and reduces overfitting.
- D
Use a smaller batch size
Why wrong: Smaller batch size can introduce noise but is not a primary regularization technique for segmentation.
- E
Dropout regularization
Dropout prevents overfitting by randomly dropping units during training.
Question 406 of 1,000
AIF-C01 AI and ML Fundamentals Practice Question
This AIF-C01 practice question tests your understanding of ai and ml fundamentals. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A team is building a deep learning model for image segmentation using Amazon SageMaker. They want to improve the model's generalization and reduce overfitting. Which THREE techniques should they apply? (Select THREE.)
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
L2 regularization on weights
L2 regularization (also known as weight decay) adds a penalty proportional to the square of the weight magnitudes to the loss function. This discourages the model from learning overly complex patterns that fit noise in the training data, directly reducing overfitting and improving generalization in deep learning models built on SageMaker.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
L2 regularization on weights
Why this is correct
L2 regularization penalizes large weights, helping generalization.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
Increase the number of layers in the network
Why it's wrong here
Adding layers increases model complexity, likely worsening overfitting.
- ✓
Data augmentation (e.g., random crops, flips)
Why this is correct
Augmentation increases effective training data size and reduces overfitting.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
Use a smaller batch size
Why it's wrong here
Smaller batch size can introduce noise but is not a primary regularization technique for segmentation.
- ✓
Dropout regularization
Why this is correct
Dropout prevents overfitting by randomly dropping units during training.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Common exam trap: answer the scenario, not the keyword
A common misconception is that increasing model complexity (more layers) or adjusting batch size are primary overfitting solutions, when in fact they are either counterproductive or secondary to explicit regularization techniques like L2, dropout, and data augmentation.
Detailed technical explanation
How to think about this question
L2 regularization works by adding λ * Σ(w²) to the loss, where λ is the regularization strength; during backpropagation, this effectively shrinks weights toward zero, preventing any single feature from dominating. In SageMaker, you can implement L2 regularization via the optimizer's weight_decay parameter (e.g., in PyTorch's AdamW or TensorFlow's Adam with decay) or by adding a kernel_regularizer in Keras layers. Dropout randomly deactivates a fraction of neurons during training, forcing the network to learn redundant representations, which improves robustness and is especially effective in fully connected layers of segmentation models.
KKey Concepts to Remember
- Read the scenario before looking for a memorised answer.
- Find the constraint that changes the correct option.
- Eliminate answers that are true in general but not in this case.
TExam Day Tips
- Watch for words such as best, first, most likely and least administrative effort.
- Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A healthcare organisation deploys an application with a public-facing web tier and a private database tier. The database subnet has no public IP and only accepts connections from the web tier's security group. Questions like this test whether you can design cloud network isolation using VNets/VPCs, subnets, and security group rules.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
- →
AI and ML Fundamentals — study guide chapter
Learn the concepts, then practise the questions
- →
AI and ML Fundamentals practice questions
Targeted practice on this topic area only
- →
All AIF-C01 questions
1,000 questions across all exam domains
- →
AWS Certified AI Practitioner AIF-C01 study guide
Full concept coverage aligned to exam objectives
- →
AIF-C01 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related AIF-C01 practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Applications of Foundation Models practice questions
Practise AIF-C01 questions linked to Applications of Foundation Models.
AI and ML Fundamentals practice questions
Practise AIF-C01 questions linked to AI and ML Fundamentals.
Security, Compliance, and Governance for AI Solutions practice questions
Practise AIF-C01 questions linked to Security, Compliance, and Governance for AI Solutions.
Fundamentals of AI and ML practice questions
Practise AIF-C01 questions linked to Fundamentals of AI and ML.
Fundamentals of Generative AI practice questions
Practise AIF-C01 questions linked to Fundamentals of Generative AI.
Generative AI and Foundation Models practice questions
Practise AIF-C01 questions linked to Generative AI and Foundation Models.
Guidelines for Responsible AI practice questions
Practise AIF-C01 questions linked to Guidelines for Responsible AI.
Security, Compliance and Governance for AI Solutions practice questions
Practise AIF-C01 questions linked to Security, Compliance and Governance for AI Solutions.
AIF-C01 fundamentals practice questions
Practise AIF-C01 questions linked to AIF-C01 fundamentals.
AIF-C01 scenario practice questions
Practise AIF-C01 questions linked to AIF-C01 scenario.
AIF-C01 troubleshooting practice questions
Practise AIF-C01 questions linked to AIF-C01 troubleshooting.
Practice this exam
Start a free AIF-C01 practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this AIF-C01 question test?
AI and ML Fundamentals — This question tests AI and ML Fundamentals — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: L2 regularization on weights — L2 regularization (also known as weight decay) adds a penalty proportional to the square of the weight magnitudes to the loss function. This discourages the model from learning overly complex patterns that fit noise in the training data, directly reducing overfitting and improving generalization in deep learning models built on SageMaker.
What should I do if I get this AIF-C01 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Keep practising
More AIF-C01 practice questions
- A data scientist is fine-tuning a foundation model on Amazon Bedrock for a custom summarization task. Which THREE practi…
- A company uses a foundation model for real-time translation in a chat application. The latency is high. Which optimizati…
- A developer is using the Amazon Bedrock API to generate text. They notice that the model sometimes returns harmful conte…
- Refer to the exhibit. A user invokes Claude v2 using the AWS CLI. The response is truncated. What is the most likely cau…
- A company wants to automatically detect anomalies in server metrics. Which algorithm is most appropriate?
- A company uses Amazon SageMaker to train a model. The training job fails with 'InsufficientInstanceCapacity' error. What…
Last reviewed: Jul 4, 2026
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.