Courseiva

AI-900 Practice Question: Describe fundamental principles of machine learning on Azure

What is a neural network?

⚠ Common exam trap

Watch out — candidates often confuse the term 'network' in 'neural network' with a computer network or distributed system, leading them to incorrectly select option A.

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

A machine learning model architecture with layers of interconnected nodes that learn representations

A neural network is a machine learning model architecture composed of layers of interconnected nodes (neurons) that process input data through weighted connections and activation functions. These layers learn hierarchical representations of data, enabling the model to capture complex patterns and relationships without explicit rule-based programming. This aligns with option B as the correct definition.

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 computer network for distributed AI training across multiple servers

    Why it's wrong here

    A computer network for distributed AI training refers to infrastructure that coordinates multiple servers or GPUs via data parallelism or model parallelism to scale compute across machines. This is a training-time engineering strategy, not a model architecture. A neural network is a self-contained function made of neurons and weights, and it remains the same architecture even when trained on a single machine or many machines.

  • A machine learning model architecture with layers of interconnected nodes that learn representations

    Why this is correct

    A neural network is a machine learning architecture composed of layers of interconnected nodes, or neurons, where each connection has an adjustable weight. Activations flow through the layers, and with non-linear activation functions the network can learn hierarchical representations from data. Training methods such as backpropagation and gradient descent update these weights so the model can identify complex patterns that would be difficult to encode explicitly.

  • A database for storing trained ML models

    Why it's wrong here

    A database for storing trained ML models is about persistent artifact management, not the model itself. Services like Azure Machine Learning model registries or blob storage hold serialized model files, but a neural network is a mathematical architecture of layers and weights that performs inference. Storing an artifact after training has nothing to do with how the model is structured internally.

  • A rule-based expert system for decision making

    Why it's wrong here

    A rule-based expert system encodes human knowledge into explicit if-then rules using symbolic reasoning, often in a knowledge base with an inference engine. In contrast, a neural network learns its own representations by adjusting weights from examples, without being given explicit decision rules. The two are fundamentally opposite approaches: hand-crafted symbolic logic versus learned sub-symbolic computations.

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 →

How Courseiva writes practice questions · Editorial policy

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.