AI-900 Practice Test 36 — 15 Questions

Question 1

A data scientist has a dataset containing information about houses: size (sq ft), number of bedrooms, location, and the actual sale price. The goal is to train a model that predicts the price of a new house based on these features. Which type of machine learning task is this?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

B) Regression. This is a regression task because the goal is to predict a continuous numeric value (the sale price) based on input features. Regression models learn the relationship between independent variables (size, bedrooms, location) and a dependent variable (price) to output a real number. In Azure Machine Learning, regression algorithms like Linear Regression, Decision Forest Regression, or Neural Network Regression would be appropriate for this scenario.

Answer

A) Classification

Answer

C) Clustering

Answer

D) Reinforcement Learning

Question 2

Match each Azure AI workload to its responsible AI principle.

Accepted Answer

Computer Vision: Ensures AI systems treat all people fairly, avoiding bias in image analysis.. Responsible AI principles guide ethical development. Computer Vision relates to fairness, NLP to inclusiveness, Speech to privacy and security, and Decision to transparency. Common confusions arise from swapping workload-specific principles.

Answer

Computer Vision: Protects user privacy by safeguarding voice data.

Answer

Speech: Ensures AI systems treat all people fairly, avoiding bias in image analysis.

Question 3

A customer support team receives thousands of emails daily. They want to automatically route each email to the appropriate department (Billing, Technical Support, or General Inquiry). They also want to extract the customer's account number and order ID from each email. Which combination of Azure AI Language features should they use?

Accepted Answer

Text classification and custom entity recognition. The scenario requires two distinct NLP tasks: categorizing emails into predefined departments (Billing, Technical Support, General Inquiry) which is a text classification task, and extracting specific structured data (account number and order ID) which requires custom entity recognition to identify domain-specific entities not covered by prebuilt NER. Azure AI Language provides both custom text classification and custom entity recognition features to handle these requirements.

Answer

Sentiment analysis and key phrase extraction

Answer

Language detection and translation

Answer

Named entity recognition (NER) and summarization

Question 4

A quality control team uses computer vision to inspect manufactured parts. They need to detect whether a part has any defects and also identify the type of defect (e.g., scratch, crack, dent) from an image. Which Azure Computer Vision capability should they use?

Accepted Answer

B: Object detection. Object detection is the correct capability because it not only identifies the presence of defects in an image but also localizes each defect with a bounding box and classifies it into specific types (e.g., scratch, crack, dent). This meets both requirements: detecting whether a part has defects and identifying the type of each defect.

Answer

A: Image classification

Answer

C: Semantic segmentation

Answer

D: Optical character recognition (OCR)

Question 5

A data scientist trains a binary classification model to predict loan defaults. The dataset contains 98% non-default cases and only 2% default cases. The model predicts 'non-default' for every instance, achieving 98% accuracy on the test set. Which metric would best reveal that the model fails to identify any actual defaults?

Accepted Answer

Recall for the default class. Recall for the default class measures the proportion of actual default cases that the model correctly identifies. With the model predicting 'non-default' for every instance, recall for the default class is 0%, because it fails to capture any true positives. This directly reveals the model's inability to detect any actual defaults, despite the high overall accuracy.

Answer

Precision for the default class

Answer

F1 score for the default class

Answer

Accuracy

Question 6

What is 'batch inference' vs 'real-time inference' in Azure Machine Learning?

Accepted Answer

Real-time processes individual requests immediately; batch processes large datasets at scheduled intervals. Batch inference processes large datasets asynchronously at scheduled intervals, making it suitable for offline or periodic predictions, while real-time inference handles individual requests immediately with low latency for interactive applications. Azure Machine Learning supports both: real-time endpoints for synchronous scoring and batch endpoints for asynchronous, high-throughput processing.

Answer

Batch inference is more accurate; real-time is faster but less accurate

Answer

Batch requires GPU compute; real-time uses CPU only

Answer

Real-time inference is only available in Azure; batch works on-premises too

Question 7

What is 'model distillation' and why might you distill a large model to a small one?

Accepted Answer

Training a smaller model to mimic a larger model's behaviour for efficient deployment. Model distillation is a technique where a smaller 'student' model is trained to replicate the behavior of a larger 'teacher' model. This is done by using the teacher's softmax outputs (logits) as training targets, allowing the student to achieve similar accuracy with far fewer parameters, making it suitable for resource-constrained environments like edge devices or real-time inference.

Answer

Extracting the essential ideas from a model's outputs into a written summary

Answer

Removing duplicate or redundant parameters from a trained model

Answer

Concentrating training data into fewer, higher-quality examples

Question 8

A company needs to extract text from scanned invoices and receipts. Which Azure services are suitable for this task? (Select all that apply.)

Accepted Answer

Computer Vision. Option A, Computer Vision, is correct because its Read/OCR capability (the Read API) extracts printed and handwritten text from images and scanned documents, which directly fits pulling text from scanned invoices and receipts. Option B, Form Recognizer, is correct because it is purpose-built for document understanding: its prebuilt receipt model and invoice model return structured fields (merchant, totals, line items, dates) from receipts and invoices, going beyond raw OCR. Option C, Text Analytics, is not suitable because it operates on already-extracted text to perform sentiment analysis, key phrase extraction, named entity recognition, and language detection—it does not perform OCR on scanned images. Option D, Custom Vision, is not suitable because it is an image classification/object detection service that labels or locates objects in images, not a text-extraction or document-understanding service.

Answer

Text Analytics

Answer

Custom Vision

Question 9

A developer uses Azure OpenAI Service to generate product reviews for an e-commerce site. The developer notices that the model often repeats the same phrases within the same review, making the output sound unnatural. Which parameter should the developer adjust to reduce this repetition?

Accepted Answer

Frequency_penalty. The frequency_penalty parameter reduces the likelihood of the model repeating the same phrases by penalizing tokens that have already appeared in the generated text. A higher frequency_penalty value (e.g., 0.5 to 1.0) discourages the model from reusing the same words or phrases, making the output more diverse and natural. This directly addresses the issue of repetitive phrasing in product reviews.

Answer

Temperature

Answer

Top_p

Answer

Max_tokens

Question 10

What is 'tool calling' (function calling) in Azure OpenAI?

Accepted Answer

A feature allowing models to specify structured calls to external functions for real-world actions. Tool calling (function calling) in Azure OpenAI is a feature that allows the model to output structured JSON requests to invoke external functions or APIs, enabling it to perform real-world actions like querying databases or sending emails. This bridges the gap between the model's static knowledge and dynamic, up-to-date data or services.

Answer

The Azure OpenAI API endpoint URL used to call the model

Answer

Calling Azure support when the AI model returns incorrect results

Answer

A billing mechanism for counting API function calls per minute

Question 11

What is the Azure AI Vision Image Analysis 4.0's 'Florence' foundation model capable of?

Accepted Answer

Advanced image understanding including detailed captions, dense captioning, and multimodal embeddings. The Florence foundation model in Azure AI Vision Image Analysis 4.0 is a multimodal model designed for advanced image understanding. It can generate detailed image captions, produce dense captions (describing multiple regions within an image), and create multimodal embeddings that align visual and textual representations for tasks like image search and similarity.

Answer

Only detecting faces in images

Answer

Only processing medical imaging for diagnostic purposes

Answer

Converting images into 3D models

Question 12

What is GitHub Copilot and how does it use AI?

Accepted Answer

An AI-powered code assistant that generates code completions and suggestions in IDEs using LLMs. GitHub Copilot is an AI-powered code assistant developed by GitHub and OpenAI. It uses large language models (LLMs), specifically a version of OpenAI's Codex model, to analyze the context of the code a developer is writing in an IDE (like VS Code) and generate real-time code completions, suggestions, and even entire functions. This directly aligns with generative AI workloads on Azure, as Copilot leverages generative AI to produce new code content based on natural language prompts or existing code patterns.

Answer

An automated GitHub Actions workflow for running CI/CD pipelines

Answer

A bot that automatically reviews and merges GitHub pull requests

Answer

A GitHub feature for visualizing code repository history

Question 13

A company is developing a chatbot that can both answer customer questions in natural language and create images on demand (e.g., 'Generate a picture of a product prototype'). Which combination of Azure generative AI models should they integrate?

Accepted Answer

A. GPT-4 for text and DALL-E for images. GPT-4 is a generative AI model optimized for natural language understanding and generation, making it ideal for answering customer questions in a conversational manner. DALL-E is a generative AI model specifically designed to create images from textual descriptions, enabling the chatbot to generate product prototypes on demand. Together, they cover both text and image generation requirements.

Answer

B. GPT-3 for text and Custom Vision for images

Answer

C. BERT for text and OCR for images

Answer

D. Language Understanding (LUIS) and Face API

Question 14

What is 'mixture of experts' (MoE) architecture and how does it relate to efficient LLMs?

Accepted Answer

An architecture with many specialised sub-networks that only activates a few per token — enabling efficient large models. Mixture of Experts (MoE) architecture splits the model into multiple specialized sub-networks (experts) and uses a gating mechanism to activate only a small subset of experts per input token. This allows the model to have a very large total parameter count while keeping the computational cost per token low, making it highly efficient for scaling large language models (LLMs) without proportionally increasing inference cost.

Answer

A training approach using multiple human experts to annotate data for different domains

Answer

Combining predictions from multiple separately trained AI models at inference time

Answer

A training technique where multiple ML experts review and validate model outputs

Question 15

What is the purpose of Azure AI Content Safety in the context of generative AI deployments?

Accepted Answer

To detect and filter harmful content in AI prompts and responses. Azure AI Content Safety is a service designed to detect and filter harmful content, such as hate speech, violence, self-harm, and sexually explicit material, in both user prompts and AI-generated responses. In generative AI deployments, this ensures that the model's outputs comply with safety policies and regulatory requirements, preventing the dissemination of offensive or dangerous content.

Answer

To compress generated content for faster delivery

Answer

To measure the quality and accuracy of AI-generated responses

Answer

To ensure AI content is written in the correct language