AI-900 Practice Question: Describe fundamental principles of machine learning on Azure
What is 'federated learning' and when is it used for privacy-preserving AI?
⚠ Common exam trap
Test-takers frequently confuse 'federated' with 'federal' or 'government-controlled' systems, or mistake federated learning for simple ensemble methods, when the core concept is decentralized training with privacy-preserving model update sharing.
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
✓
Distributed training where devices share model updates (not raw data) — enabling privacy-preserving collaborative learning
Federated learning is a distributed machine learning technique where the model is trained across multiple decentralized devices or servers holding local data, without exchanging the raw data itself. Instead, only model updates (e.g., gradients or weights) are shared with a central server, which aggregates them to improve the global model. This approach preserves privacy because sensitive data never leaves the local device, making it ideal for scenarios like healthcare, finance, or mobile keyboard prediction where data cannot be centralized due to regulatory or privacy constraints.
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 data from multiple countries governed by a federal legal system
Why it's wrong here
The term 'federal' in federated learning refers to the federation of participating devices or clients, not a federal legal system or jurisdiction. Training on multinational data governed by a single federal law is a data governance and compliance issue, not a machine learning architecture. Federated learning instead distributes training across devices while keeping raw data local, so legal jurisdiction is orthogonal to how the model is trained.
- ✓
Distributed training where devices share model updates (not raw data) — enabling privacy-preserving collaborative learning
Why this is correct
Federated learning is a distributed training technique where each participant trains on its own local data and only shares model updates—such as gradients or weights—with a central aggregator. This enables a shared model to be improved collaboratively across multiple organizations without exposing sensitive raw data. Because raw data never leaves the local device, the approach provides privacy-preserving collaborative learning. This exactly matches the definition of federated learning.
- ✗
A training approach where a federal government agency controls access to all training data
Why it's wrong here
This describes centralized data governance, where a federal agency owns or controls the training data, which is a policy and security arrangement rather than a training methodology. Federated learning, by contrast, is a technical architecture that decentralizes training: data stays at the edge and only model parameters are exchanged. There is no central authority that directly controls all data; instead, participants collectively train a model. Thus, this option misunderstands the 'federation' as governmental control.
- ✗
Combining predictions from models trained independently at multiple research institutions
Why it's wrong here
Combining predictions from independently trained models is an ensemble learning strategy—for example, bagging or random forests—that aggregates outputs at inference time to improve accuracy. Federated learning is fundamentally different: it trains a single model collaboratively by exchanging model updates during the iterative training process, not by merging separate models' predictions. Participants in federated learning contribute to the same shared model, so the final output comes from one model, not a vote or average of many models.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
Key term
Prediction
Prediction is the process of using data and algorithms to forecast future outcomes or identify patterns without explicit programming for each scenario.
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
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.