- A
A random sampling method for selecting training data without replacement
Why wrong: Data sampling is dataset management — SGD uses mini-batches to compute gradients for weight updates during training.
- B
An optimisation algorithm that updates weights using gradients computed on random data mini-batches
SGD computes cheap gradient estimates from mini-batches — trading noise for speed, enabling training on large datasets.
- C
A technique for randomly selecting which model architecture to use for AutoML
Why wrong: Architecture selection is model search — SGD is an optimiser for updating weights within a chosen architecture.
- D
Randomly descending through decision tree branches to make predictions
Why wrong: Tree traversal is inference in decision trees — SGD is a gradient-based weight update algorithm for neural networks and linear models.
Quick Answer
The correct answer is that stochastic gradient descent (SGD) is an optimization algorithm that updates model weights using gradients computed on random data mini-batches. This is correct because, unlike batch gradient descent which processes the entire dataset in one pass, SGD introduces beneficial noise by selecting a small, random subset of training data for each weight update. This noise actually helps the model escape local minima and converge faster, while also drastically reducing memory usage since the full dataset doesn't need to be loaded at once. On the Microsoft Azure AI Fundamentals AI-900 exam, this concept tests your understanding of how Azure Machine Learning optimizes model training, often appearing in questions about training algorithms or hyperparameter tuning. A common trap is confusing SGD with batch gradient descent—remember that the "stochastic" part refers to the random selection of mini-batches, not the entire dataset. Memory tip: think "SGD = Small, Greedy, Daring"—it takes small, random steps that are greedy for speed and daring enough to skip the full dataset.
AI-900 Practice Question: Describe fundamental principles of machine learning on Azure
This AI-900 practice question tests your understanding of describe fundamental principles of machine learning on azure. 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.
What is 'stochastic gradient descent' (SGD) and how does it work?
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
An optimisation algorithm that updates weights using gradients computed on random data mini-batches
Stochastic Gradient Descent (SGD) is an optimization algorithm used to train machine learning models by iteratively updating model weights. It computes the gradient of the loss function on a randomly selected mini-batch of training data (not the entire dataset), which introduces noise but significantly speeds up convergence and reduces memory usage. This mini-batch approach is the core of SGD and distinguishes it from batch gradient descent.
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.
- ✗
A random sampling method for selecting training data without replacement
Why it's wrong here
Data sampling is dataset management — SGD uses mini-batches to compute gradients for weight updates during training.
- ✓
An optimisation algorithm that updates weights using gradients computed on random data mini-batches
Why this is correct
SGD computes cheap gradient estimates from mini-batches — trading noise for speed, enabling training on large datasets.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
A technique for randomly selecting which model architecture to use for AutoML
Why it's wrong here
Architecture selection is model search — SGD is an optimiser for updating weights within a chosen architecture.
- ✗
Randomly descending through decision tree branches to make predictions
Why it's wrong here
Tree traversal is inference in decision trees — SGD is a gradient-based weight update algorithm for neural networks and linear models.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates confuse 'stochastic' with 'random sampling of data' (Option A) or 'random model selection' (Option C), when in fact SGD's stochasticity refers to using random mini-batches to compute gradients, not random data selection or architecture choice.
Detailed technical explanation
How to think about this question
Under the hood, SGD updates weights using the formula θ = θ - η * ∇L(θ; x_i, y_i), where η is the learning rate and ∇L is the gradient computed on a mini-batch. A subtle behavior is that the stochastic noise from mini-batches can help escape local minima, but it also causes variance in the loss curve; techniques like learning rate scheduling and momentum are often added to stabilize training. In real-world scenarios like training deep neural networks on Azure, SGD with mini-batches is essential for handling large datasets (e.g., millions of images) that cannot fit into memory all at once.
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
An e-commerce site experiences heavy traffic on Black Friday and near-zero traffic during off-peak weeks. Rather than provisioning permanent large VMs, the team uses auto-scaling groups that add capacity automatically under load and reduce it overnight. Questions like this test whether you understand elasticity, availability zones, and cloud compute scaling patterns.
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.
- →
Describe fundamental principles of machine learning on Azure — study guide chapter
Learn the concepts, then practise the questions
- →
Describe fundamental principles of machine learning on Azure practice questions
Targeted practice on this topic area only
- →
All AI-900 questions
1,020 questions across all exam domains
- →
Microsoft Azure AI Fundamentals AI-900 study guide
Full concept coverage aligned to exam objectives
- →
AI-900 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related AI-900 practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Describe Artificial Intelligence workloads and considerations practice questions
Practise AI-900 questions linked to Describe Artificial Intelligence workloads and considerations.
Describe fundamental principles of machine learning on Azure practice questions
Practise AI-900 questions linked to Describe fundamental principles of machine learning on Azure.
Describe features of computer vision workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of computer vision workloads on Azure.
Describe features of Natural Language Processing workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of Natural Language Processing workloads on Azure.
Describe features of generative AI workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of generative AI workloads on Azure.
AI-900 fundamentals practice questions
Practise AI-900 questions linked to AI-900 fundamentals.
AI-900 scenario practice questions
Practise AI-900 questions linked to AI-900 scenario.
AI-900 troubleshooting practice questions
Practise AI-900 questions linked to AI-900 troubleshooting.
Practice this exam
Start a free AI-900 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 AI-900 question test?
Describe fundamental principles of machine learning on Azure — This question tests Describe fundamental principles of machine learning on Azure — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: An optimisation algorithm that updates weights using gradients computed on random data mini-batches — Stochastic Gradient Descent (SGD) is an optimization algorithm used to train machine learning models by iteratively updating model weights. It computes the gradient of the loss function on a randomly selected mini-batch of training data (not the entire dataset), which introduces noise but significantly speeds up convergence and reduces memory usage. This mini-batch approach is the core of SGD and distinguishes it from batch gradient descent.
What should I do if I get this AI-900 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 →
Last reviewed: Jun 11, 2026
This AI-900 practice question is part of Courseiva's free Microsoft 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 AI-900 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.