AI-900: Microsoft Azure AI Fundamentals Exam: Quick Revision Notes

Hello there! I recently took the AI-900 exam, while preparing for the exam, I made some notes, sharing them here so someone might find them helpful.

Note: I assume that you have already gone through the course in detail. These notes do not go through the details of the topics in depth but are short/pointers/notes that can help you quickly revise them just before the exam.

Also, I have added some exam tips, that will help you to get to the correct answers.

Table of Contents

Section 1: Describe Artificial Intelligence workloads and considerations (20โ€“25%)

Section 2: Describe fundamental principles of machine learning on Azure (25โ€“30%)

Section 3: Describe features of computer vision workloads on Azure (15โ€“20%)

Section 4: Describe features of Natural Language Processing (NLP) workloads on Azure (25โ€“30%)

Section 1: Describe Artificial Intelligence workloads and considerations (20โ€“25%)

Topics: Identify features of common AI workloads

  • Identify features of anomaly detection workloads
  • Identify computer vision workloads
  • Identify natural language processing workloads
  • Identify knowledge mining workloads
Sr.No Topic/Question Notes
1. What is AI? Artificial Intelligence (AI) is the creation of software that imitates human behaviors and capabilities
2. What is ML? Machine Learning (ML) is a subset of AI that helps teach a computer model to make predictions and draw conclusions from data.
3. Types of ML Methods?
  1. Supervised Learning: Find patterns in data based on labeled input data. Example: Regression & Classification.
  2. Unsupervised Learning: Pattern discovery without labeled data using Unsupervised Learning. Example: Clustering
3. Anomaly Detection

A ML-based technique that analyzes data over time and identifies unusual changes.

  • Credit Card transactions fraud detection.
  • Network intrusion detection.
  • Machine failure prediction.

Azure Service: Anomaly Detector: Foresee problems before they occur

4. Computer Vision Area of AI that deals with visual processing.
5. Tasks of Computer Vision
  • Image classification: Training ML model to classify images based on their contents. Example: classify images based on the type of vehicle they contain, such as taxis, buses, cyclists.
    ML - Image classification
  • Object detection: Training ML models to classify individual objects within an image, and identify their location with a bounding box.
    ML Object Detection
  • Semantic segmentation: ML technique in which individual pixels in the image are classified according to the object to which they belong.
    ML - Semantic segmentation
  • Image analysis: A combination of ML models and advanced image analysis techniques to extract information from images, including tags, descriptive captions that summarize the scene shown in the image.
    ML - Image analysis
  • Face detection, analysis, and recognition: A specialized form of object detection that locates human faces in an image.
    ML - Face Detection
  • Optical character recognition (OCR): Detect and read text in images
    ML - Optical character recognition - OCR
6. Microsoft Azure: Computer vision services
  • Computer Vision
  • Custom Vision
  • Face
  • Form Recognizer
7. What is NLP? Natural language processing (NLP): area of AI that deals with creating software that understands written and spoken language.
8. NLP Workloads
  • Automatically translate spoken or written phrases between languages.
  • Analyze and interpret text in documents, email messages, and other sources.
  • Interpret commands and determine appropriate actions.
  • Interpret spoken language, and synthesize speech responses.
9. Microsoft Azure: NLP services
  • Language
  • Translator
  • Speech
  • Azure Bot
10. What is knowledge mining? Extracting information from large volumes of often unstructured data to create a searchable knowledge store.
11. Microsoft Azure: Knowledge Mining services Azure Cognitive Search

Topics: Identify guiding principles for responsible AI

  • Describe considerations for fairness in an AI solution
  • Describe considerations for reliability and safety in an AI solution
  • Describe considerations for privacy and security in an AI solution
  • Describe considerations for inclusiveness in an AI solution
  • Describe considerations for transparency in an AI solution
  • Describe considerations for accountability in an AI solution
Sr.No. Topic/Questions Notes
1. Challenges and risks with AI
  • Bias can affect results - dealing with fairness.
  • Errors may cause harm - dealing with reliability.
  • Data could be exposed - dealing with privacy and safety.
  • Solutions may not work for everyone - dealing with inclusiveness.
  • Users must trust a complex system - dealing with transparency.
  • Who's liable for AI-driven decisions? - dealing with accountability.
2. Examples of Microsoft AI Principles
  1. Fairness: A loan-approval model discriminates by gender due to bias in the data with which it was trained
  2. Reliability: An autonomous vehicle experiences a system failure and causes a collision
  3. Privacy & Safety: A medical diagnostic bot is trained using sensitive patient data, which is stored insecurely
  4. Inclusiveness: A home automation assistant provides no audio output for visually impaired users
  5. Transparency: An AI-based financial tool makes investment recommendations - what are they based on?
  6. Accountability: An innocent person is convicted of a crime based on evidence from facial recognition โ€“ who's responsible?

Section 2: Describe fundamental principles of machine learning on Azure (25โ€“30%)

Topics: Identify common machine learning types

  • Identify regression machine learning scenarios
  • Identify classification machine learning scenarios
  • Identify clustering machine learning scenarios
Sr.No. Topic/Question Notes
1. What is Regression in Machine Learning Regression models is a type of Supervised Learning used to predicts a numeric label or outcome based on variables, or features
2. Feature The input values/columns to the regression model to predict a label
3. Label The numeric output value to be predicted.
4. Regression ML scenarios
  • Predict house rent (label) based on features: size, city, population, etc..
  • Predict crop yield (label) based on features: weather, solid, temperature, etc.
  • Predict future advertisement click based on past data.

Exam Tip: If the question is to predict and the the answer is a numeric value then its is related to regression.

5. What is Classification in Machine Learning It is a type of Supervised Learning technique used to predict categories or classes.
6. Classification ML scenarios
  • Will it snow tomorrow?
  • Will he buy a car?
  • Will they win the game?
  • Is this Email a spam?

Exam Tip: If the answer to a question to predict is in terms of a definite Yes/No then its a question on classification.

Exam Tip: Confusion Matrix is used to assess the quality of a classification model's predictions.

7. What is Clustering in Machine Learning It is a type of unsupervised machine learning technique. It is used to group similar entities based on their features.
8. Clustering ML scenarios
  1. Identify distinct customer segments based on their purchase history.
  2. Cluster website visitors based on their browsing interests.
  3. Group social media posts based on the topics.
  4. Classify patient health records to identify distinct groups with similar medical conditions
  5. Exam Tip: If the question is related to segmenting, clustering, classification or grouping and the data is not labeled (i.e unsupervised) then the question is about clustering.

Topics: Describe core machine learning concepts

  • Identify features and labels in a dataset for machine learning
  • Describe how training and validation datasets are used in machine learning
Sr.No. Topic/Question Notes
1. Examples of identify features and labels in a dataset for machine learning
  • Predict fair of a taxi-journey.
    • Features: distance for the journey, traffic, type of taxi.
    • Lable: fair of the taxi-journey.
  • Identify label and features for sales prediction - date, time, footfalls, sales, discounts?
    • Features:: date, time, footfalls, discounts
    • Label: sales
  • Predicting the price of a house:
    • Features: Number of bedrooms, Square footage, Location, Age of the house
    • Label: Price of the house
  • Predicting student performance:
    • Features: Study hours, Previous exam scores, Attendance, Study habits
    • Label: Exam score
2. How training and validation datasets are used in machine learning
  1. Inject Dataset
  2. Prepare Dataset - Identify Features and Label, Clean and Transform the data.
  3. Split the data randomly into training and validation data.
  4. Train the model using ML Technique.
  5. Evaluate the model with the validation data.
  6. Deploy the model
3. Confusion Matrix:

It is used to assess the quality of a Classification Model's predictions.

Example: Does the patient has Covid-19?
  • True Positive: Model predicts the patient has Covid-19, and the patient does actually have Covid-19.
  • False Positive: Model predicts the patient has Covid-19, but the patient doesn't actually have Covid-19.
  • False Negative: Model predicts the patient doesn't have Covid-19, but the patient actually does have Covid-19.
  • True Negative: Model predicts the patient doesn't have Covid-19, and the patient actually doesn't have Covid-19.
  • AI - Confusion Matrix Diagram - True Positive - True Negative - False Positive - False Negative
4. Metrics that can be derived from the Confusion Matrix:
  • Accuracy
  • Precision
  • Recall (True positive rate)
  • F1 Score
5. Binary Classification model Predicted probability is a value between 0 and 1
6. ROC Curve Plotting the True Positive Rate (y-axis) and False Postive Rate (x-axis) for every possible threshold value between 0 and 1 results in a curve is known as the ROC curve.
7. Inference Pipeline

Used to automate your model into a service that makes continuous predictions.

8. Endpoint

Once the pipeline is ready you can do deployment of your model at an endpoint

Topics: Describe capabilities of visual tools in Azure Machine Learning Studio

  • Automated machine learning
  • Azure Machine Learning designer
Sr.No Topic/Question Notes
1. Azure Android Machine Learning Service Service that helps simplify tasks such as:
  • Prepare data
  • Train a model
  • Deploy a model
2. Azure Machine Learning Compute
  • Compute Instances: These are development workstations that data scientists can use to work with data and models.
  • Compute Clusters: These are scalable clusters of virtual machines for on-demand processing of experiment code.
  • Inference Clusters: These are deployment targets for predictive services that use your trained models.
  • Attached Compute: These links are to existing Azure compute resources, such as Virtual Machines or Azure Databricks clusters.

Section 3: Describe features of computer vision workloads on Azure (15โ€“20%)

Topic: Identify common types of computer vision solution

  • Identify features of image classification solutions
  • Identify features of object detection solutions
  • Identify features of optical character recognition solutions
  • Identify features of facial detection and facial analysis solutions

Topic: Identify Azure tools and services for computer vision tasks

  • Identify capabilities of the Computer Vision service
  • Identify capabilities of the Custom Vision service
  • Identify capabilities of the Face service
  • Identify capabilities of the Form Recognizer service
1. Computer Vision: To extract information from images.
2. Computer vision workloads:
  • Content Organization
  • Text Extraction
  • Spatial Analysis
3. Computer Vision Service Used to analyze images, and return detailed information about an image and the objects it depicts.
4. Types of Azure Computer Vision Services
  1. Computer Vision:

    A specific resource for the Computer Vision service.

    Exam Tip: Use this type of resource if,

    1. You don't intend to use any other cognitive services.

    2. You want to track utilization and costs for your Computer Vision resource separately.

  2. Cognitive Services:

    A general cognitive services resource that includes Computer Vision along with many other cognitive services (such as Text Analytics, Translator Text, etc.)

    Exam Tip: Use this type of resource if,

    1. You intend to use multiple other cognitive services.

    2. To simplify administration and development.

    Exam Tip:

    For both the resources you get,

    1. A key: It is used to authenticate client applications.

    2. An endpoint: To provide the HTTP address at which your resource can be accessed.

5. Usecases of Azure Computer Vision Service
  1. Describing an image: A large building in a city.
  2. Tagging images: Metadata that summarizes attributes of the image: example - car, tower, building.
  3. Object detection: Tag with a bounding box coordinates.
  4. Brands detection: Identify know brands from a image.
  5. Image detection: Can detect and analyze human faces in an image, including the ability to determine age and a bounding box rectangle for the location of the face(s).
  6. Image categorization: Example - people_, people_group, animal_ , animal_birds. There are 86 categories.
  7. Domain-Specific Content detection: Known Celebrities and Landmarks.
  8. Optical character recognition (OCR): Detect printed and handwritten text in images.
  9. Image types detection: for example, identifying clip art images or line drawings.
  10. Image color schemes detection- specifically, identifying the dominant foreground, background, and overall colors in an image.
  11. Generate thumbnails: creating small versions of images.
  12. Moderate content: detecting images that contains that violates security and privacy.

Section 4: Describe features of Natural Language Processing (NLP) workloads on Azure (25โ€“30%)

Topics: Identify features of common NLP workload scenarios

  • Identify features and uses for key phrase extraction
  • Identify features and uses for entity recognition
  • Identify features and uses for sentiment analysis
  • Identify features and uses for language modeling
  • Identify features and uses for speech recognition and synthesis
  • Identify features and uses for translation

Topics: Identify Azure tools and services for NLP workloads

  • Identify capabilities of the Language service
  • Identify capabilities of the Speech service
  • Identify capabilities of the Translator service

Sr.No Topic/Question Notes
1. Natural Language Processing (NLP) Usecases
  1. Text mining
  2. Text analysis
  3. Sentiment analysis
  4. Key phrase extraction
  5. Named entity recognition
  6. Language detection
2. Text Analytics Techniques
  1. Statistical analysis: Removal of stop words (a, an..)
  2. Frequency analysis: counting how often each word appears
  3. N-grams: a two-word phrase is a bi-gram, a three-word phrase is a tri-gram, and so on
  4. Stemming/Lemmatization: Algorithms to normalize words before counting them: example: walk, walked, walking.
  5. Noun phrase: Breaking down sentences into tree-like structures such
  6. Sentiment Analysis: Encoding words as numeric features to train a machine learning model. Workload: Classify a document as positive or negative sentiments.
  7. Vectorized Models: Models that capture semantic relationships between words by assigning them to locations in n-dimensional space.
3. Workloads of Language Cognitive Service
  • Identify the language of the text - e.g. English, German, Swedish etc.
  • Sentement Analysis of the text - positive/negative sentiments.
  • Key phrases extraction from text for point taking.
  • Identify and categorize entities in the text - people, places, organizations, dates, times, quantities etc.
4. Language detection service capabilities:
  • Provides the language name: example: "English"
  • Provides the ISO 6391 language code: example en
  • Provides a numeric score (0.1-1.0) - the confidence in the language detection
Exam Tip:

If the text proivded is ambiguous in nature, the language service will return a unknown for language and NaN as the score.

Exam Tip:

A score of 0.5 might indicate that the sentiment of the text is indeterminate.

5. Language Service: Key phrase extraction

Evaluating the text of a document, or documents, and then identifying the main talking points of the document(s)


Text: Code2care is an initiative to publish and share varied knowledge in technical and technical areas gathered during day-to-day learnings and development activities. People can leverage this portal to find solutions to their various queries without re-inventing the wheel by referring to our easy to understand posts.

Key phrases:

  • Code2care - tech knowledge initiative
  • Varied technical knowledge sharing
  • Day-to-day learnings and development
  • Solutions for queries
  • Easy-to-understand posts
  • People can leverage this portal
6. Langauge Service: Entity recognition

From the provided unstructured text get a list of entities in the text that it recognizes.

Example: "Andrew likes to walk in NYC Central Park in the evening"
Entity: Andrew
Type: Person
Entity: NYC Central Park
Type: Location
Entity: evening
Type: DateTime or Time
7. Speech Recognition To detect and interpret spoken input (speech-to-text)
8. Speech Recognition - Usecases
  • To providing closed captions for recorded or live videos
  • For creating a transcript of a phone call or meeting
  • Automated note dictation
  • To determining intended user input for further processing

Speech-to-text API can be used for real-time and batch transcription

9. Speech Synthesis

To generate spoken output.

Azure Service: Speech to text API

10. Speech Synthesis

To generate spoken output (text-to-speech)

Azure Service: Text to speech API

11. Speech Synthesis - Usecases
  • To generating spoken responses to user input.
  • To create voice menus for telephone systems.
  • For reading email or text messages aloud in hands-free scenarios.
  • To broadcasting announcements in public locations, such as railway stations or airports.
12. Azure Translator Service

Text-to-text translation.

Uses a Neural Machine Translation (NMT) model for translation.

Supports more than 60 languages.

Can simultaneously translate a source document into multiple languages.

Optional Configurations:
  1. Profanity filtering
  2. Selective translation: Tag code, a brand name, or a word/phrase
13. Azure Speech Service

Speech-to-text and speech-to-speech translation.

Speech to text

Text to speech

Speech Translation - used to translate speech in one language to text or speech in another.

14. Conversational Language Understanding of Language Service
  • Utterances: something a user might say
    "Turn off the light"
    "Switch on the TV"
  • Entities: Ttem to which an utterance refers.
    "Turn off the light" - entity: light
    "Switch on the TV" - entity: TV
  • Intents: The purpose, or goal, expressed in a user's utterance.
    "Turn off the light" - purpose: off a device
    "Switch on the TV" - purpose: on a device
15. How to create an application with Conversational Language Understanding?
  1. Authoring the model: by defining entities, intents, and utterances.
  2. Publish the model: For intent and entity prediction based on user input.
Exam Tip:

Use the Language portal for authoring and to use the SDK for runtime predictions.

16. Types of entities:
  1. Machine-Learned
  2. List
  3. RegEx
  4. Pattern.any

Topics: Identify considerations for conversational AI solutions on Azure

  • identify features and uses for bots
  • identify capabilities of the Azure Bot service
Sr.No Topic/Question Notes
1. Bot Solution: Combination of,

1. Language Service:
Custom question answering feature that enables you to create a knowledge base of question and answer pairs that can be queried using natural language input.

2. Azure Bot Service: Framework for developing, publishing, and managing bots on Azure.

3. Where is Knowledge base deployed? Over a REST interface.
4. How can Client Application access the Knowledge base deployed?
  1. The knowledge base ID
  2. The knowledge base endpoint
  3. The knowledge base authorization key
5. Connect channels Multiple channels that makes it possible for users to interact with it through web chat, email, Microsoft Teams, and other common communication media.

Facing issues? Have Questions? Post them here! I am happy to answer!

Author Info:

Rakesh (He/Him) has over 14+ years of experience in Web and Application development. He is the author of insightful How-To articles for Code2care.

Follow him on: X

You can also reach out to him via e-mail:

Copyright ยฉ Code2care 2024 | Privacy Policy | About Us | Contact Us | Sitemap