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.
Refereced Documentation: https://learn.microsoft.com/en-us/certifications/exams/ai-900/
Also, I have added some exam tips, that will help you to get to the correct answers.
Section 1: Describe Artificial Intelligence workloads and considerations (20–25%)
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
|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?||
A ML-based technique that analyzes data over time and identifies unusual changes.Examples:
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||
|6.||Microsoft Azure: Computer vision services||
|7.||What is NLP?||Natural language processing (NLP): area of AI that deals with creating software that understands written and spoken language.|
|9.||Microsoft Azure: NLP services||
|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
|1.||Challenges and risks with AI||
|2.||Examples of Microsoft AI Principles||
Section 2: Describe fundamental principles of machine learning on Azure (25–30%)
Topics: Identify common machine learning types
- Identify regression machine learning scenarios
- Identify classification machine learning scenarios
- Identify clustering machine learning scenarios
|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||
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||
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||
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
|1.||Examples of identify features and labels in a dataset for machine learning|
|2.||How training and validation datasets are used in machine learning||
It is used to assess the quality of a Classification Model's predictions.Example: Does the patient has Covid-19?
|4.||Metrics that can be derived from the Confusion Matrix:||
|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.|
Used to automate your model into a service that makes continuous predictions.
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
|1.||Azure Android Machine Learning Service||Service that helps simplify tasks such as:
|2.||Azure Machine Learning Compute||
Section 3: Describe features of computer vision workloads on Azure (15–20%)
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:||
|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||
|5.||Usecases of Azure Computer Vision Service||
Section 4: Describe features of Natural Language Processing (NLP) workloads on Azure (25–30%)
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
|1.||Natural Language Processing (NLP) Usecases||
|2.||Text Analytics Techniques||
|3.||Workloads of Language Cognitive Service||
|4.||Language detection service capabilities:||
If the text proivded is ambiguous in nature, the language service will return a unknown for language and NaN as the score.
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)Example:
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.
|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"
|7.||Speech Recognition||To detect and interpret spoken input (speech-to-text)|
|8.||Speech Recognition - Usecases||
Speech-to-text API can be used for real-time and batch transcription
To generate spoken output.
Azure Service: Speech to text API
To generate spoken output (text-to-speech)
Azure Service: Text to speech API
|11.||Speech Synthesis - Usecases||
|12.||Azure Translator Service||
Uses a Neural Machine Translation (NMT) model for translation.
Supports more than 60 languages.
Can simultaneously translate a source document into multiple languages.
|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||
|15.||How to create an application with Conversational Language Understanding?||
Use the Language portal for authoring and to use the SDK for runtime predictions.
|16.||Types of entities:||
Topics: Identify considerations for conversational AI solutions on Azure
- identify features and uses for bots
- identify capabilities of the Azure Bot service
|1.||Bot Solution:||Combination of,
1. Language Service:
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?||
|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!
- Lost your iPhone? Regenerate QR Code for Microsoft Authenticator App
- What is Microsoft 365 Message You are using more licenses on your trial than what you will purchase once the free trial ends.
- Power BI error Something went wrong, unable to read the application metadata
- How to save a file as csv in Windows Notepad?
- You're not on Teams yet, but you can set it up for your organization. [Microsoft Teams Login Error]
- Fix- Microsoft Word Pages Appear Black
- How To Remove Only Conditional Formatting in Excel
- How to record PowerPoint slide show presentation on Mac - narration, slide timings, ink gestures
- Fix 0x80070194 Error When Opening Microsoft OneDrive File
- 0xCAA20003: You ran into an authorization problem. [Microsoft]
- PowerShell git: The term git is not recognized as the name of a cmdlet
- Remove mailto link from Microsoft 365 Word Document Email Text
- How to take a screenshot on Microsoft Windows OS on PC or Laptop
- How to Force Quit Microsoft Excel Application on Mac
- [fix] Microsoft Error Code 0x80004005 - Unspecified error
- How to Delete a Sheet in Excel on Mac
- How to add Business Users using Microsoft 365 Admin Center
- [Microsoft Teams 4c7] Modern authentication failed here, but you'll still be able to sign in. Your status code is 4c7 error
- Fix Microsoft Store Error Code: 0x80072EFD
- How to add Data Analysis Add-in in Excel on Mac
- How to Select Two Separate Columns in Excel on Mac
- Internet Explorer browser auto redirect to Microsoft Edge for compatibility with modern web sites
- How to Create Absolute References in Microsoft Excel for Mac
- What is FCM Messages Test Notification! [Microsoft Teams] [Google Hangouts]
- How to Sync Microsoft Teams Calendar with Mac Calendar
- Bootstrap Nav Menu Dropdown on hover - Bootstrap
- Android : IOException: Unable to open sync connection! - Android
- 22: Send Yahoo! Email using smtplib - SMTP protocol client using Python Program - Python-Programs
- Java 7 addSuppression() and getSuppression() Exception Handling - Java
- How to delete a dir or folder using Python code - Python
- How to turn on channel notifications for Microsoft Teams - Teams
- Open PowerShell Terminal in Visual Studio Code (VSCode) - Powershell