AI-900 Practice Question: Describe fundamental principles of machine learning on Azure
What is 'neural architecture search' (NAS) and how does it relate to AutoML?
⚠ Common exam trap
Many exam-takers confuse NAS with simply searching for existing models online or in a database, rather than understanding it as an automated, generative search process that creates new architectures.
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
✓
Automating the discovery of optimal neural network architectures using computational search
Neural Architecture Search (NAS) is an automated process that uses computational search methods—such as reinforcement learning, evolutionary algorithms, or gradient-based optimization—to discover optimal neural network architectures for a given task. It is a key component of AutoML because AutoML aims to automate the entire machine learning pipeline, including model selection and hyperparameter tuning, and NAS specifically automates the design of the neural network topology itself.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Searching the web for neural network architectures published in research papers
Why it's wrong here
Searching the web for published architectures (e.g., reading arXiv papers or blog posts) is a literature search, where a human reads and manually selects architectures that other researchers designed. This is a passive, human-driven research activity and does not involve automated generation, mutation, or iterative evaluation of new candidates. NAS automates the entire design cycle inside a computer, evaluating thousands of candidate networks algorithmically, so this option describes a research workflow, not the underlying computational technique of NAS.
- ✓
Automating the discovery of optimal neural network architectures using computational search
Why this is correct
Neural Architecture Search (NAS) is an automated, iterative optimization process that explores a defined space of possible network designs—such as layer types, depth, width, and connectivity—using methods like reinforcement learning, evolutionary algorithms, or gradient-based approaches. Each candidate architecture is trained and evaluated on validation data, and the search algorithm uses those performance signals to propose better candidates. This allows NAS to discover novel, high-performing architectures that may surpass human-designed networks, making it a computational search rather than a retrieval or manual process.
- ✗
Querying a database of pre-built neural networks to find the closest match for a task
Why it's wrong here
Querying a pre-built model repository (e.g., TensorFlow Hub, PyTorch Hub, or the ONNX Model Zoo) is a model selection or retrieval task: you compare metadata, benchmarks, or embeddings to find an existing architecture that someone else already designed and trained. No new architecture is generated or evaluated during this process; the candidate set is fixed and finite. NAS, in contrast, uses algorithms to generate and evaluate novel candidates from an expansive (often infinite) search space, so this option is a form of reuse, not automated discovery.
- ✗
A legal search process for patenting new AI model architectures
Why it's wrong here
A legal patent search involves examining prior art, patent claims, and infringement risks in intellectual property law—it is a legal and administrative procedure, not a technical method for designing neural networks. NAS is an AI research technique that computationally generates and evaluates model architectures using data and objective functions. The two are fundamentally unrelated: patent search seeks legal protection or clearance, while NAS seeks optimal predictive performance.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
Key term
Machine learning
Machine learning is a branch of artificial intelligence where computers learn patterns from data to make decisions or predictions without being explicitly programmed for every task.
Key term
AutoML
Automated Machine Learning (AutoML) is a set of tools and techniques that automate the process of building, training, and tuning machine learning models without requiring deep expertise in data science.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. 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.