Courseiva

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

What is the difference between 'training' and 'inference' in machine learning?

⚠ Common exam trap

Many exam-takers confuse the terms 'training' and 'inference' as interchangeable or domain-specific, when in fact they represent distinct lifecycle phases with different computational and operational requirements in Azure Machine 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 creates models from data; inference uses trained models to make predictions

Training is the phase where a machine learning model learns patterns from labeled or unlabeled data by adjusting its internal parameters (e.g., weights in a neural network) to minimize a loss function. Inference is the subsequent phase where the trained model applies those learned patterns to new, unseen data to generate predictions or classifications. In Azure Machine Learning, training typically involves running a script on a compute target (e.g., a GPU cluster) and registering the resulting model, while inference is performed by deploying that model as a real-time endpoint or batch pipeline.

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 creates models from data; inference uses trained models to make predictions

    Why this is correct

    Training is the learning phase: an algorithm iteratively adjusts its internal parameters (weights and biases) by minimizing a loss function on labeled examples, capturing statistical patterns in the data. Inference is the production phase: the trained, frozen model performs a forward pass on new, unseen data to output predictions rapidly, without any parameter updates, enabling real-world use.

  • Training is for testing models; inference is for training them

    Why it's wrong here

    This statement reverses the two phases. Training is the phase in which the model learns from labeled data by updating weights; it is not a testing activity. Inference applies the already-learned parameters to new inputs to make predictions and does not update the model. Model evaluation uses a separate validation or test set, which is distinct from inference.

  • They are the same process with different names for clarity

    Why it's wrong here

    Training and inference are fundamentally different processes, not just labels. Training uses backpropagation and optimization algorithms like stochastic gradient descent to adjust model parameters and is computationally expensive, requiring hours on GPUs. Inference is a single forward pass with fixed parameters, optimized for low latency and high throughput, so the two phases are mechanistically and operationally distinct.

  • Training is for image models; inference is for text models

    Why it's wrong here

    This is false because both training and inference apply to every data modality. An image classifier, such as a convolutional neural network, is trained on pixel data and later infers object classes; a text model, such as a transformer, is trained on tokens and infers word sequences. The actual distinction is always between learning parameters and using them, not between image and text inputs.

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.