AI-900 Practice Question: Describe features of computer vision workloads on Azure
What is 'few-shot learning' in the context of Azure AI Custom Vision model training?
⚠ Common exam trap
Test-takers frequently confuse 'few-shot learning' with resource-saving techniques like reduced compute or early stopping, when the core concept is about achieving high accuracy with minimal labeled data through transfer learning.
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
✓
Training an accurate vision model with very few labelled examples using transfer learning
Few-shot learning in Azure AI Custom Vision refers to training an accurate vision model with very few labeled examples by leveraging transfer learning. This approach uses a pre-trained neural network (e.g., ResNet) as a starting point, allowing the model to learn new visual concepts from as few as 2–5 images per class, significantly reducing the data collection burden.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Training a model using only a small subset of available compute resources
Why it's wrong here
This option misidentifies few-shot learning as a constraint on hardware resources. Few-shot learning concerns the quantity of labelled data—training a model with only a handful of examples per category—not the amount of compute available. Compute limitations would be addressed via Azure's scaling or managed compute, whereas few-shot methods rely on transferring pre-learned features from a large base model.
- ✓
Training an accurate vision model with very few labelled examples using transfer learning
Why this is correct
This is correct because Azure Custom Vision supports few-shot vision training by starting from a pre-trained model and fine-tuning it with just a small number of labelled images—often as few as 15 per class. Transfer learning lets the convolutional base retain generic feature extractors (edges, shapes, textures) while only the final classification head adapts to the new categories. That is the essence of few-shot learning: achieving high accuracy from very limited labelled examples.
- ✗
A technique for running multiple small training experiments in parallel
Why it's wrong here
Running multiple small training experiments in parallel describes distributed hyperparameter tuning or a sweep across configurations, which is a way to search for the best model settings. Few-shot learning, however, refers to the size of the labelled dataset used for a single training run—only a few examples per class. Parallelizing experiments does not reduce the data requirement and has no inherent connection to transfer learning or sample efficiency.
- ✗
Limiting training to the first few hundred iterations regardless of convergence
Why it's wrong here
This option confuses a training stopping criterion with the defining attribute of few-shot learning. Capping training at a few hundred iterations, or using early stopping when validation loss plateaus, is a practical measure to prevent overfitting or save time, but it says nothing about how much labelled data is available. Few-shot learning is characterized by the extreme scarcity of labelled examples, not by the number of optimization steps performed.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
Key term
Neural network
A neural network is a computing system modeled loosely on the human brain that learns to recognize patterns from data without being explicitly programmed for every rule.
About these practice questions
One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.