Before I can make the content to deliver a certification preparation session on YouTube, I spend a lot of time researching each topic from the exam objectives. My goal is to get the source as close as possible to the topic and always be a Microsoft source. Sometimes these are hard to get them right, but I think I often get many of them spot on :). But if you want to dig through all the links I researched…. they’re all below!
Subscribe to my YouTube Channel at https://aka.ms/Azure/CERT to see the updates as I publish these AI-102 sessions over the next few weeks! If you’ve never watched my sessions, let me explain my goal. It is NOT to teach you everything. As you can see from the links below IT IS A LOT. I used to deliver these 1-hour sessions at Microsoft TechReady, Ready and Ignite. I tell people that what I’ve observed in over two decades of being an MCT is that most people miss passing an exam by 3-5 questions. Therefore, my goal with these sessions is to get you 3-5 more questions to help you pass. But you have to do the hard work first e.g. go through Microsoft Learn modules and practice exams at a minimum. THEN, come back and watch my AI-102, or any other session on my Channel, to help tip you over.
CAUTION – I know I pack a lot in, in 1-1.5 hours. But the beauty of YouTube. You can pause rewind, listen as many times as you want!
- Preparing for AI-102 – Plan and manage an Azure AI solution (Part 1 of 6) | Microsoft Learn
- Collections | Microsoft Learn
Skills at a glance
- Plan and manage an Azure AI solution (15–20%)
- Implement content moderation solutions (10–15%)
- Implement computer vision solutions (15–20%)
- Implement natural language processing solutions (30–35%)
- Implement knowledge mining and document intelligence solutions (10–15%)
- Implement generative AI solutions (10–15%)
Plan and manage an Azure AI solution (15–20%)
Select the appropriate Azure AI service
- Select the appropriate service for a computer vision solution
- Select the appropriate service for a natural language processing solution
- Select the appropriate service for a speech solution
- Select the appropriate service for a generative AI solution
- Select the appropriate service for a document intelligence solution
- Select the appropriate service for a knowledge mining solution
Plan, create and deploy an Azure AI service
- Plan for a solution that meets Responsible AI principles
- Create an Azure AI resource
- Determine a default endpoint for a service
- Integrate Azure AI services into a continuous integration and continuous delivery (CI/CD) pipeline
- Plan and implement a container deployment
Manage, monitor, and secure an Azure AI service
- Configure diagnostic logging
Manage diagnostic logging – Training
- Monitor an Azure AI resource
- Manage costs for Azure AI services
- Manage account keys
- Protect account keys by using Azure Key Vault
- Manage authentication for an Azure AI Service resource
- Manage private communications
Implement content moderation solutions (10–15%)
Create solutions for content delivery
- Implement a text moderation solution with Azure AI Content Safety
- Implement an image moderation solution with Azure AI Content Safety
Implement computer vision solutions (15–20%)
Analyze images
- Select visual features to meet image processing requirements
- Detect objects in images and generate image tags
- Include image analysis features in an image processing request
- Interpret image processing responses
- Extract text from images using Azure AI Vision
- Convert handwritten text using Azure AI Vision
Implement custom computer vision models by using Azure AI Vision
Custom Vision documentation – Quickstarts, Tutorials, API Reference – Azure AI services
- Choose between image classification and object detection models
- Label images
- Train a custom image model, including image classification and object detection
- Evaluate custom vision model metrics
- Publish a custom vision model
- Consume a custom vision model
Analyze videos
- Use Azure AI Video Indexer to extract insights from a video or live stream
- Use Azure AI Vision Spatial Analysis to detect presence and movement of people in video
Implement natural language processing solutions (30–35%)
Analyze text by using Azure AI Language What is Azure AI Language
- Extract key phrases
- Extract entities
- Determine sentiment of text
- Detect the language used in text
- Detect personally identifiable information (PII) in text
Process speech by using Azure AI Speech
- Implement text-to-speech
- Implement speech-to-text
- Improve text-to-speech by using Speech Synthesis Markup Language (SSML)
- Implement custom speech solutions
- Implement intent recognition
- Implement keyword recognition
Translate language
- Translate text and documents by using the Azure AI Translator service
- Implement custom translation, including training, improving, and publishing a custom model
- Translate speech-to-speech by using the Azure AI Speech service
- Translate speech-to-text by using the Azure AI Speech service
- Translate to multiple languages simultaneously
Implement and manage a language understanding model by using Azure AI Language
- Create intents and add utterances
- Create entities
- What is entity linking in Azure AI Language? – Azure AI services
- Entity components in conversational language understanding – Azure AI services
- Train, evaluate, deploy, and test a language understanding model
- How to train and evaluate models in Conversational Language Understanding
- How to deploy a model for conversational language understanding – Azure AI services
- Test the Model
- How to use train and test – Azure AI services
- Optimize a language understanding model
- Consume a language model from a client application
- Backup and recover language understanding models
Create a custom question answering solution by using Azure AI Language
- Create a custom question answering project
- Add question-and-answer pairs manually
- Import sources
- Train and test a knowledge base
- Publish a knowledge base
- Create a multi-turn conversation
- Add alternate phrasing
- Add chit-chat to a knowledge base
- Export a knowledge base
- Create a multi-language question answering solution
Implement knowledge mining and document intelligence solutions (10–15%)
Implement an Azure AI Search solution
- Provision an Azure AI Search resource
- Create data sources
- Create an index
- Define a skillset
- Implement custom skills and include them in a skillset
- Create and run an indexer
- Query an index, including syntax, sorting, filtering, and wildcards
- Manage Knowledge Store projections, including file, object, and table projections
Implement an Azure AI Document Intelligence solution
- Provision a Document Intelligence resource
- Create a Document Intelligence resource
- Use prebuilt models to extract data from documents
- Implement a custom document intelligence model
- Train, test, and publish a custom document intelligence model
- Create a composed document intelligence model
- Implement a document intelligence model as a custom Azure AI Search skill
Implement generative AI solutions (10–15%)
Use Azure OpenAI Service to generate content
- Provision an Azure OpenAI Service resource
- Select and deploy an Azure OpenAI model
- Submit prompts to generate natural language
- Submit prompts to generate code
- Use the DALL-E model to generate images
- Use Azure OpenAI APIs to submit prompts and receive responses
Optimize generative AI
- Configure parameters to control generative behavior
- Apply prompt engineering techniques to improve responses
- Use your own data with an Azure OpenAI model
- Fine-tune an Azure OpenAI model
From <https://learn.microsoft.com/en-us/credentials/certifications/resources/study-guides/ai-102>
AllergicToCode 